From e489ad7a210f4234db696d1f2749d5f3662fa65b Mon Sep 17 00:00:00 2001 From: Russell Bryant Date: Sun, 2 Feb 2025 14:58:18 -0500 Subject: [PATCH] [Misc] Add SPDX-License-Identifier headers to python source files (#12628) - **Add SPDX license headers to python source files** - **Check for SPDX headers using pre-commit** commit 9d7ef44c3cfb72ca4c32e1c677d99259d10d4745 Author: Russell Bryant Date: Fri Jan 31 14:18:24 2025 -0500 Add SPDX license headers to python source files This commit adds SPDX license headers to python source files as recommended to the project by the Linux Foundation. These headers provide a concise way that is both human and machine readable for communicating license information for each source file. It helps avoid any ambiguity about the license of the code and can also be easily used by tools to help manage license compliance. The Linux Foundation runs license scans against the codebase to help ensure we are in compliance with the licenses of the code we use, including dependencies. Having these headers in place helps that tool do its job. More information can be found on the SPDX site: - https://spdx.dev/learn/handling-license-info/ Signed-off-by: Russell Bryant commit 5a1cf1cb3b80759131c73f6a9dddebccac039dea Author: Russell Bryant Date: Fri Jan 31 14:36:32 2025 -0500 Check for SPDX headers using pre-commit Signed-off-by: Russell Bryant --------- Signed-off-by: Russell Bryant --- .buildkite/check-wheel-size.py | 2 + .buildkite/generate_index.py | 2 + .../test_lm_eval_correctness.py | 1 + .../convert-results-json-to-markdown.py | 2 + .../scripts/download-tokenizer.py | 2 + .../scripts/generate-nightly-markdown.py | 2 + .../scripts/get-lmdeploy-modelname.py | 2 + .../scripts/summary-nightly-results.py | 2 + .pre-commit-config.yaml | 6 ++- benchmarks/backend_request_func.py | 2 + benchmarks/benchmark_guided.py | 1 + benchmarks/benchmark_latency.py | 1 + .../benchmark_long_document_qa_throughput.py | 1 + benchmarks/benchmark_prefix_caching.py | 1 + benchmarks/benchmark_prioritization.py | 1 + benchmarks/benchmark_serving.py | 1 + benchmarks/benchmark_serving_guided.py | 1 + benchmarks/benchmark_throughput.py | 1 + .../cutlass_benchmarks/sparse_benchmarks.py | 2 + benchmarks/cutlass_benchmarks/utils.py | 2 + .../cutlass_benchmarks/w8a8_benchmarks.py | 2 + .../cutlass_benchmarks/weight_shapes.py | 2 + .../disagg_prefill_proxy_server.py | 2 + .../disagg_benchmarks/round_robin_proxy.py | 2 + .../visualize_benchmark_results.py | 2 + .../fused_kernels/layernorm_rms_benchmarks.py | 2 + benchmarks/kernels/benchmark_aqlm.py | 2 + benchmarks/kernels/benchmark_layernorm.py | 2 + benchmarks/kernels/benchmark_lora.py | 2 + benchmarks/kernels/benchmark_machete.py | 2 + benchmarks/kernels/benchmark_marlin.py | 2 + benchmarks/kernels/benchmark_moe.py | 2 + .../kernels/benchmark_paged_attention.py | 2 + benchmarks/kernels/benchmark_quant.py | 2 + benchmarks/kernels/benchmark_rmsnorm.py | 2 + benchmarks/kernels/benchmark_rope.py | 2 + benchmarks/kernels/benchmark_shapes.py | 2 + benchmarks/kernels/graph_machete_bench.py | 2 + benchmarks/kernels/utils.py | 2 + benchmarks/kernels/weight_shapes.py | 2 + benchmarks/overheads/benchmark_hashing.py | 2 + cmake/hipify.py | 2 + collect_env.py | 2 + .../vllm_cutlass_library_extension.py | 2 + csrc/quantization/machete/generate.py | 2 + docs/source/conf.py | 2 + docs/source/generate_examples.py | 2 + examples/offline_inference/aqlm_example.py | 2 + examples/offline_inference/arctic.py | 2 + examples/offline_inference/audio_language.py | 1 + examples/offline_inference/basic.py | 2 + .../basic_with_model_default_sampling.py | 2 + examples/offline_inference/chat.py | 2 + examples/offline_inference/chat_with_tools.py | 2 + examples/offline_inference/classification.py | 2 + examples/offline_inference/cli.py | 2 + examples/offline_inference/cpu_offload.py | 2 + examples/offline_inference/distributed.py | 1 + examples/offline_inference/embedding.py | 2 + examples/offline_inference/encoder_decoder.py | 1 + .../offline_inference/florence2_inference.py | 1 + examples/offline_inference/gguf_inference.py | 2 + .../offline_inference/llm_engine_example.py | 2 + .../lora_with_quantization_inference.py | 1 + examples/offline_inference/mlpspeculator.py | 2 + .../offline_inference/multilora_inference.py | 1 + examples/offline_inference/neuron.py | 2 + .../neuron_int8_quantization.py | 2 + examples/offline_inference/pixtral.py | 2 + examples/offline_inference/prefix_caching.py | 2 + examples/offline_inference/profiling.py | 2 + .../profiling_tpu/profiling.py | 2 + examples/offline_inference/rlhf.py | 1 + .../offline_inference/save_sharded_state.py | 1 + examples/offline_inference/scoring.py | 2 + .../offline_inference/simple_profiling.py | 2 + .../offline_inference/structured_outputs.py | 2 + .../offline_inference/torchrun_example.py | 1 + examples/offline_inference/tpu.py | 2 + examples/offline_inference/vision_language.py | 1 + .../vision_language_embedding.py | 1 + .../vision_language_multi_image.py | 1 + examples/offline_inference/whisper.py | 2 + examples/online_serving/api_client.py | 1 + .../online_serving/cohere_rerank_client.py | 1 + .../gradio_openai_chatbot_webserver.py | 2 + examples/online_serving/gradio_webserver.py | 2 + .../online_serving/jinaai_rerank_client.py | 1 + .../openai_chat_completion_client.py | 2 + ...i_chat_completion_client_for_multimodal.py | 1 + ...penai_chat_completion_client_with_tools.py | 1 + ...enai_chat_completion_structured_outputs.py | 2 + .../openai_chat_completion_with_reasoning.py | 1 + ...hat_completion_with_reasoning_streaming.py | 1 + ...ai_chat_embedding_client_for_multimodal.py | 2 + .../openai_completion_client.py | 2 + .../openai_cross_encoder_score.py | 1 + .../online_serving/openai_embedding_client.py | 2 + .../online_serving/openai_pooling_client.py | 1 + .../opentelemetry/dummy_client.py | 2 + examples/other/tensorize_vllm_model.py | 2 + find_cuda_init.py | 2 + python_only_dev.py | 2 + setup.py | 2 + tests/async_engine/api_server_async_engine.py | 1 + tests/async_engine/test_api_server.py | 2 + tests/async_engine/test_async_llm_engine.py | 2 + tests/async_engine/test_request_tracker.py | 2 + .../test_basic_correctness.py | 1 + .../basic_correctness/test_chunked_prefill.py | 1 + tests/basic_correctness/test_cpu_offload.py | 2 + tests/basic_correctness/test_cumem.py | 2 + tests/basic_correctness/test_preemption.py | 1 + tests/compile/backend.py | 2 + tests/compile/piecewise/test_simple.py | 1 + tests/compile/piecewise/test_toy_llama.py | 1 + tests/compile/test_basic_correctness.py | 2 + tests/compile/test_full_graph.py | 2 + tests/compile/test_functionalization.py | 2 + tests/compile/test_fusion.py | 2 + tests/compile/test_pass_manager.py | 2 + tests/compile/test_wrapper.py | 2 + tests/compile/utils.py | 2 + tests/conftest.py | 2 + tests/core/block/conftest.py | 2 + tests/core/block/e2e/conftest.py | 2 + tests/core/block/e2e/test_correctness.py | 2 + .../e2e/test_correctness_sliding_window.py | 2 + tests/core/block/test_block_manager.py | 2 + tests/core/block/test_block_table.py | 2 + tests/core/block/test_common.py | 2 + .../block/test_cpu_gpu_block_allocator.py | 2 + tests/core/block/test_naive_block.py | 2 + tests/core/block/test_prefix_caching_block.py | 2 + tests/core/test_chunked_prefill_scheduler.py | 2 + tests/core/test_num_computed_tokens_update.py | 2 + tests/core/test_scheduler.py | 2 + tests/core/test_scheduler_encoder_decoder.py | 2 + tests/core/test_serialization.py | 2 + tests/core/utils.py | 2 + tests/distributed/test_ca_buffer_sharing.py | 2 + tests/distributed/test_comm_ops.py | 1 + tests/distributed/test_custom_all_reduce.py | 2 + tests/distributed/test_distributed_oot.py | 2 + .../distributed/test_multi_node_assignment.py | 1 + tests/distributed/test_pipeline_parallel.py | 1 + tests/distributed/test_pipeline_partition.py | 2 + tests/distributed/test_pp_cudagraph.py | 2 + tests/distributed/test_pynccl.py | 2 + tests/distributed/test_same_node.py | 2 + tests/distributed/test_shm_broadcast.py | 2 + tests/distributed/test_torchrun_example.py | 2 + tests/distributed/test_utils.py | 2 + tests/encoder_decoder/test_e2e_correctness.py | 1 + .../output_processor/test_multi_step.py | 2 + .../output_processor/test_stop_checker.py | 2 + tests/engine/test_arg_utils.py | 2 + tests/engine/test_computed_prefix_blocks.py | 2 + tests/engine/test_custom_executor.py | 2 + tests/engine/test_detokenization.py | 2 + tests/engine/test_multiproc_workers.py | 2 + tests/engine/test_short_mm_context.py | 2 + tests/engine/test_skip_tokenizer_init.py | 2 + tests/engine/test_stop_reason.py | 1 + tests/engine/test_stop_strings.py | 2 + tests/entrypoints/conftest.py | 2 + tests/entrypoints/llm/test_accuracy.py | 1 + tests/entrypoints/llm/test_chat.py | 2 + tests/entrypoints/llm/test_collective_rpc.py | 2 + tests/entrypoints/llm/test_encode.py | 2 + tests/entrypoints/llm/test_generate.py | 2 + .../llm/test_generate_multiple_loras.py | 2 + tests/entrypoints/llm/test_gpu_utilization.py | 2 + tests/entrypoints/llm/test_guided_generate.py | 2 + tests/entrypoints/llm/test_init.py | 2 + tests/entrypoints/llm/test_lazy_outlines.py | 2 + .../entrypoints/llm/test_prompt_validation.py | 2 + .../offline_mode/test_offline_mode.py | 1 + .../test_deepseekr1_reasoning_parser.py | 2 + .../openai/reasoning_parsers/utils.py | 2 + tests/entrypoints/openai/test_accuracy.py | 1 + .../openai/test_async_tokenization.py | 2 + tests/entrypoints/openai/test_audio.py | 2 + tests/entrypoints/openai/test_basic.py | 2 + tests/entrypoints/openai/test_chat.py | 2 + tests/entrypoints/openai/test_chat_echo.py | 2 + .../entrypoints/openai/test_chat_template.py | 2 + .../entrypoints/openai/test_chunked_prompt.py | 2 + tests/entrypoints/openai/test_cli_args.py | 2 + tests/entrypoints/openai/test_completion.py | 2 + tests/entrypoints/openai/test_embedding.py | 2 + .../openai/test_encoder_decoder.py | 2 + .../entrypoints/openai/test_lora_adapters.py | 2 + tests/entrypoints/openai/test_metrics.py | 2 + tests/entrypoints/openai/test_models.py | 2 + .../openai/test_oot_registration.py | 2 + tests/entrypoints/openai/test_pooling.py | 2 + .../openai/test_prompt_validation.py | 2 + tests/entrypoints/openai/test_rerank.py | 2 + .../openai/test_return_tokens_as_ids.py | 2 + tests/entrypoints/openai/test_root_path.py | 2 + tests/entrypoints/openai/test_run_batch.py | 2 + tests/entrypoints/openai/test_score.py | 2 + tests/entrypoints/openai/test_serving_chat.py | 2 + .../entrypoints/openai/test_serving_models.py | 2 + tests/entrypoints/openai/test_shutdown.py | 2 + tests/entrypoints/openai/test_tokenization.py | 2 + tests/entrypoints/openai/test_video.py | 2 + tests/entrypoints/openai/test_vision.py | 2 + .../openai/test_vision_embedding.py | 2 + .../tool_parsers/test_pythonic_tool_parser.py | 2 + .../entrypoints/openai/tool_parsers/utils.py | 2 + tests/entrypoints/test_chat_utils.py | 2 + tests/kernels/allclose_default.py | 2 + tests/kernels/conftest.py | 2 + tests/kernels/quant_utils.py | 2 + tests/kernels/test_activation.py | 2 + tests/kernels/test_aqlm.py | 2 + tests/kernels/test_attention.py | 2 + tests/kernels/test_attention_selector.py | 2 + tests/kernels/test_awq.py | 2 + tests/kernels/test_awq_marlin.py | 1 + tests/kernels/test_awq_triton.py | 1 + tests/kernels/test_block_fp8.py | 2 + tests/kernels/test_blocksparse_attention.py | 2 + tests/kernels/test_cache.py | 2 + tests/kernels/test_cascade_flash_attn.py | 2 + tests/kernels/test_causal_conv1d.py | 2 + tests/kernels/test_cutlass.py | 1 + tests/kernels/test_cutlass_2of4_sparse.py | 1 + tests/kernels/test_encoder_decoder_attn.py | 1 + tests/kernels/test_flash_attn.py | 2 + tests/kernels/test_flashinfer.py | 2 + tests/kernels/test_fp8_quant.py | 2 + tests/kernels/test_fused_quant_layernorm.py | 2 + tests/kernels/test_ggml.py | 2 + tests/kernels/test_gguf.py | 2 + tests/kernels/test_gptq.py | 2 + tests/kernels/test_int8_quant.py | 2 + tests/kernels/test_layernorm.py | 2 + tests/kernels/test_machete_mm.py | 1 + tests/kernels/test_mamba_ssm.py | 2 + tests/kernels/test_marlin_gemm.py | 1 + tests/kernels/test_mha_attn.py | 1 + tests/kernels/test_moe.py | 1 + tests/kernels/test_permute_cols.py | 2 + tests/kernels/test_pos_encoding.py | 2 + tests/kernels/test_prefix_prefill.py | 2 + tests/kernels/test_rotary_embedding.py | 1 + tests/kernels/test_triton_decode_attention.py | 2 + tests/kernels/test_triton_scaled_mm.py | 1 + tests/kernels/test_utils.py | 1 + tests/kernels/utils.py | 1 + tests/kv_transfer/disagg_test.py | 2 + tests/kv_transfer/module_test.py | 2 + tests/kv_transfer/test_lookup_buffer.py | 2 + tests/kv_transfer/test_send_recv.py | 2 + tests/lora/conftest.py | 2 + tests/lora/data/long_context_test_data.py | 2 + tests/lora/test_baichuan.py | 2 + tests/lora/test_chatglm3_tp.py | 2 + tests/lora/test_gemma.py | 2 + tests/lora/test_jamba.py | 2 + tests/lora/test_layers.py | 2 + tests/lora/test_llama_tp.py | 2 + tests/lora/test_long_context.py | 2 + tests/lora/test_lora_bias_e2e.py | 2 + tests/lora/test_lora_checkpoints.py | 2 + tests/lora/test_lora_huggingface.py | 2 + tests/lora/test_lora_manager.py | 2 + tests/lora/test_minicpmv_tp.py | 2 + tests/lora/test_mixtral.py | 2 + tests/lora/test_peft_helper.py | 2 + tests/lora/test_phi.py | 2 + tests/lora/test_punica_ops_sizes.py | 1 + tests/lora/test_punica_ops_variation.py | 1 + tests/lora/test_quant_model.py | 2 + tests/lora/test_qwen2vl.py | 2 + tests/lora/test_tokenizer_group.py | 2 + tests/lora/test_utils.py | 2 + tests/lora/test_worker.py | 2 + tests/lora/utils.py | 2 + tests/metrics/test_metrics.py | 2 + tests/model_executor/conftest.py | 2 + .../model_executor/test_enabled_custom_ops.py | 2 + .../model_executor/test_guided_processors.py | 2 + .../test_model_load_with_params.py | 2 + tests/model_executor/weight_utils.py | 2 + .../audio_language/test_ultravox.py | 2 + .../models/decoder_only/language/test_aqlm.py | 1 + .../models/decoder_only/language/test_fp8.py | 2 + .../models/decoder_only/language/test_gguf.py | 1 + .../decoder_only/language/test_gptq_marlin.py | 1 + .../language/test_gptq_marlin_24.py | 1 + .../decoder_only/language/test_granite.py | 1 + .../decoder_only/language/test_jamba.py | 2 + .../decoder_only/language/test_mamba.py | 1 + .../decoder_only/language/test_mistral.py | 1 + .../decoder_only/language/test_modelopt.py | 2 + .../decoder_only/language/test_models.py | 1 + .../decoder_only/language/test_phimoe.py | 1 + .../decoder_only/vision_language/test_awq.py | 2 + .../vision_language/test_h2ovl.py | 2 + .../vision_language/test_intern_vit.py | 2 + .../vision_language/test_models.py | 1 + .../vision_language/test_phi3v.py | 2 + .../vision_language/test_pixtral.py | 1 + .../vision_language/test_qwen2_vl.py | 2 + .../vision_language/vlm_utils/builders.py | 1 + .../vlm_utils/case_filtering.py | 1 + .../vision_language/vlm_utils/core.py | 3 +- .../vlm_utils/custom_inputs.py | 1 + .../vision_language/vlm_utils/model_utils.py | 1 + .../vision_language/vlm_utils/runners.py | 1 + .../vision_language/vlm_utils/types.py | 1 + .../embedding/language/test_cls_models.py | 1 + .../embedding/language/test_embedding.py | 1 + .../models/embedding/language/test_gritlm.py | 2 + .../models/embedding/language/test_scoring.py | 1 + tests/models/embedding/utils.py | 2 + .../vision_language/test_dse_qwen2_vl.py | 2 + .../vision_language/test_llava_next.py | 2 + .../embedding/vision_language/test_phi3v.py | 2 + .../audio_language/test_whisper.py | 1 + .../encoder_decoder/language/test_bart.py | 1 + .../vision_language/test_broadcast.py | 2 + .../vision_language/test_florence2.py | 2 + .../vision_language/test_mllama.py | 2 + .../multimodal/processing/test_common.py | 2 + .../multimodal/processing/test_idefics3.py | 1 + .../multimodal/processing/test_internvl.py | 1 + .../multimodal/processing/test_llava_next.py | 2 + .../processing/test_llava_onevision.py | 2 + .../multimodal/processing/test_phi3v.py | 1 + .../multimodal/processing/test_qwen2_vl.py | 2 + tests/models/registry.py | 2 + tests/models/test_initialization.py | 2 + tests/models/test_oot_registration.py | 2 + tests/models/test_registry.py | 2 + tests/models/utils.py | 2 + tests/mq_llm_engine/test_abort.py | 1 + tests/mq_llm_engine/test_error_handling.py | 1 + tests/mq_llm_engine/test_load.py | 1 + tests/mq_llm_engine/utils.py | 2 + .../multi_step/test_correctness_async_llm.py | 2 + tests/multi_step/test_correctness_llm.py | 2 + tests/multimodal/test_inputs.py | 2 + tests/multimodal/test_processing.py | 2 + tests/multimodal/test_processor_kwargs.py | 2 + tests/multimodal/test_utils.py | 2 + tests/multimodal/utils.py | 2 + tests/neuron/test_prefix_prefill.py | 2 + tests/plugins/vllm_add_dummy_model/setup.py | 2 + .../vllm_add_dummy_model/__init__.py | 2 + .../my_gemma_embedding.py | 2 + .../vllm_add_dummy_model/my_llava.py | 2 + .../vllm_add_dummy_model/my_opt.py | 2 + .../plugins/vllm_add_dummy_platform/setup.py | 2 + .../vllm_add_dummy_platform/__init__.py | 2 + .../dummy_attention_backend.py | 2 + .../vllm_add_dummy_platform/dummy_platform.py | 2 + tests/plugins_tests/test_platform_plugins.py | 2 + .../test_disable_sliding_window.py | 1 + tests/prefix_caching/test_prefix_caching.py | 1 + tests/prompt_adapter/test_bloom.py | 2 + .../test_multi_adapter_inference.py | 2 + tests/prompt_adapter/test_pa_lora.py | 2 + tests/quantization/test_bitsandbytes.py | 1 + tests/quantization/test_compressed_tensors.py | 1 + tests/quantization/test_configs.py | 1 + tests/quantization/test_cpu_offload.py | 2 + tests/quantization/test_experts_int8.py | 2 + tests/quantization/test_fp8.py | 1 + tests/quantization/test_ipex_quant.py | 1 + tests/quantization/test_lm_head.py | 1 + tests/quantization/test_quark.py | 1 + .../test_register_quantization_config.py | 1 + tests/quantization/utils.py | 2 + .../test_runai_model_streamer_loader.py | 2 + .../runai_model_streamer/test_weight_utils.py | 2 + tests/samplers/test_beam_search.py | 1 + tests/samplers/test_ignore_eos.py | 1 + tests/samplers/test_logits_processor.py | 2 + tests/samplers/test_logprobs.py | 2 + tests/samplers/test_no_bad_words.py | 1 + tests/samplers/test_ranks.py | 2 + tests/samplers/test_rejection_sampler.py | 1 + tests/samplers/test_sampler.py | 2 + tests/samplers/test_seeded_generate.py | 1 + .../test_typical_acceptance_sampler.py | 1 + tests/spec_decode/e2e/conftest.py | 2 + tests/spec_decode/e2e/test_compatibility.py | 2 + .../spec_decode/e2e/test_eagle_correctness.py | 1 + tests/spec_decode/e2e/test_integration.py | 1 + .../e2e/test_integration_dist_tp2.py | 1 + .../e2e/test_integration_dist_tp4.py | 1 + tests/spec_decode/e2e/test_logprobs.py | 2 + .../e2e/test_medusa_correctness.py | 1 + tests/spec_decode/e2e/test_mlp_correctness.py | 1 + .../e2e/test_multistep_correctness.py | 1 + .../spec_decode/e2e/test_ngram_correctness.py | 1 + tests/spec_decode/e2e/test_seed.py | 2 + tests/spec_decode/test_batch_expansion.py | 2 + tests/spec_decode/test_dynamic_spec_decode.py | 2 + tests/spec_decode/test_metrics.py | 2 + tests/spec_decode/test_multi_step_worker.py | 2 + tests/spec_decode/test_ngram_worker.py | 2 + tests/spec_decode/test_scorer.py | 2 + tests/spec_decode/test_spec_decode_worker.py | 2 + tests/spec_decode/test_utils.py | 2 + tests/spec_decode/utils.py | 2 + tests/standalone_tests/lazy_torch_compile.py | 2 + tests/tensorizer_loader/conftest.py | 2 + tests/tensorizer_loader/test_tensorizer.py | 2 + tests/test_cache_block_hashing.py | 1 + tests/test_config.py | 2 + tests/test_embedded_commit.py | 2 + tests/test_inputs.py | 2 + tests/test_logger.py | 2 + tests/test_logits_processor.py | 2 + tests/test_regression.py | 1 + tests/test_sampling_params.py | 1 + tests/test_scalartype.py | 2 + tests/test_sequence.py | 2 + tests/test_sharded_state_loader.py | 2 + tests/test_utils.py | 2 + tests/tokenization/test_cached_tokenizer.py | 2 + tests/tokenization/test_detokenize.py | 2 + tests/tokenization/test_get_eos.py | 1 + tests/tokenization/test_tokenizer.py | 2 + tests/tokenization/test_tokenizer_group.py | 2 + tests/tool_use/conftest.py | 2 + ...est_chat_completion_request_validations.py | 2 + tests/tool_use/test_chat_completions.py | 2 + tests/tool_use/test_jamba_tool_parser.py | 2 + tests/tool_use/test_parallel_tool_calls.py | 2 + tests/tool_use/test_tool_calls.py | 2 + tests/tool_use/utils.py | 2 + tests/tpu/test_compilation.py | 2 + tests/tpu/test_custom_dispatcher.py | 2 + tests/tpu/test_quantization_accuracy.py | 2 + tests/tracing/test_tracing.py | 2 + tests/utils.py | 2 + tests/v1/core/test_kv_cache_utils.py | 2 + tests/v1/core/test_prefix_caching.py | 1 + tests/v1/e2e/test_cascade_attention.py | 2 + tests/v1/engine/test_async_llm.py | 2 + tests/v1/engine/test_engine_args.py | 2 + tests/v1/engine/test_engine_core.py | 2 + tests/v1/engine/test_engine_core_client.py | 2 + tests/v1/engine/test_output_processor.py | 2 + tests/v1/sample/test_sampler.py | 2 + tests/v1/test_stats.py | 2 + tests/v1/test_utils.py | 2 + tests/v1/worker/test_gpu_input_batch.py | 2 + tests/vllm_test_utils/setup.py | 2 + .../vllm_test_utils/__init__.py | 1 + .../vllm_test_utils/vllm_test_utils/blame.py | 2 + .../vllm_test_utils/monitor.py | 2 + tests/weight_loading/test_weight_loading.py | 2 + .../test_encoder_decoder_model_runner.py | 2 + tests/worker/test_model_input.py | 2 + tests/worker/test_model_runner.py | 2 + tests/worker/test_profile.py | 2 + tests/worker/test_swap.py | 2 + tools/check_spdx_header.py | 43 +++++++++++++++++++ tools/profiler/print_layerwise_table.py | 2 + tools/profiler/visualize_layerwise_profile.py | 2 + tools/report_build_time_ninja.py | 2 + use_existing_torch.py | 2 + vllm/__init__.py | 1 + vllm/_custom_ops.py | 2 + vllm/_ipex_ops.py | 2 + vllm/adapter_commons/layers.py | 2 + vllm/adapter_commons/models.py | 2 + vllm/adapter_commons/request.py | 2 + vllm/adapter_commons/utils.py | 2 + vllm/adapter_commons/worker_manager.py | 2 + vllm/assets/audio.py | 2 + vllm/assets/base.py | 2 + vllm/assets/image.py | 2 + vllm/assets/video.py | 2 + vllm/attention/__init__.py | 2 + vllm/attention/backends/abstract.py | 2 + vllm/attention/backends/blocksparse_attn.py | 2 + vllm/attention/backends/flash_attn.py | 1 + vllm/attention/backends/flashinfer.py | 2 + vllm/attention/backends/hpu_attn.py | 2 + vllm/attention/backends/ipex_attn.py | 1 + vllm/attention/backends/mla/utils.py | 2 + vllm/attention/backends/openvino.py | 2 + vllm/attention/backends/pallas.py | 2 + vllm/attention/backends/placeholder_attn.py | 2 + vllm/attention/backends/rocm_flash_attn.py | 1 + vllm/attention/backends/torch_sdpa.py | 1 + vllm/attention/backends/triton_mla.py | 2 + vllm/attention/backends/utils.py | 1 + vllm/attention/backends/xformers.py | 1 + vllm/attention/layer.py | 1 + .../blocksparse_attention_kernel.py | 2 + .../ops/blocksparse_attention/interface.py | 2 + .../ops/blocksparse_attention/utils.py | 2 + vllm/attention/ops/hpu_paged_attn.py | 2 + vllm/attention/ops/ipex_attn.py | 2 + vllm/attention/ops/nki_flash_attn.py | 2 + vllm/attention/ops/paged_attn.py | 2 + vllm/attention/ops/prefix_prefill.py | 2 + vllm/attention/ops/triton_decode_attention.py | 2 + vllm/attention/ops/triton_flash_attention.py | 2 + vllm/attention/selector.py | 2 + vllm/beam_search.py | 2 + vllm/compilation/backends.py | 2 + vllm/compilation/counter.py | 2 + vllm/compilation/decorators.py | 2 + vllm/compilation/fix_functionalization.py | 2 + vllm/compilation/fusion.py | 2 + vllm/compilation/fx_utils.py | 2 + vllm/compilation/inductor_pass.py | 2 + vllm/compilation/monitor.py | 2 + vllm/compilation/multi_output_match.py | 2 + vllm/compilation/pass_manager.py | 2 + vllm/compilation/reshapes.py | 2 + vllm/compilation/vllm_inductor_pass.py | 2 + vllm/compilation/wrapper.py | 2 + vllm/config.py | 2 + vllm/connections.py | 2 + vllm/core/block/block_table.py | 2 + vllm/core/block/common.py | 2 + vllm/core/block/cpu_gpu_block_allocator.py | 2 + vllm/core/block/interfaces.py | 2 + vllm/core/block/naive_block.py | 2 + vllm/core/block/prefix_caching_block.py | 1 + vllm/core/block/utils.py | 1 + vllm/core/block_manager.py | 1 + vllm/core/evictor.py | 2 + vllm/core/interfaces.py | 2 + vllm/core/placeholder_block_space_manager.py | 2 + vllm/core/scheduler.py | 2 + vllm/device_allocator/cumem.py | 2 + vllm/distributed/__init__.py | 2 + vllm/distributed/communication_op.py | 2 + .../device_communicators/cuda_wrapper.py | 1 + .../device_communicators/custom_all_reduce.py | 2 + .../custom_all_reduce_utils.py | 2 + .../device_communicators/hpu_communicator.py | 2 + .../device_communicators/pynccl.py | 2 + .../device_communicators/pynccl_wrapper.py | 2 + .../device_communicators/shm_broadcast.py | 2 + .../device_communicators/tpu_communicator.py | 2 + .../device_communicators/xpu_communicator.py | 2 + .../kv_transfer/kv_connector/base.py | 1 + .../kv_transfer/kv_connector/factory.py | 2 + .../kv_connector/simple_connector.py | 1 + .../kv_transfer/kv_lookup_buffer/base.py | 1 + .../kv_lookup_buffer/simple_buffer.py | 1 + vllm/distributed/kv_transfer/kv_pipe/base.py | 1 + .../kv_transfer/kv_pipe/mooncake_pipe.py | 2 + .../kv_transfer/kv_pipe/pynccl_pipe.py | 1 + .../kv_transfer/kv_transfer_agent.py | 1 + vllm/distributed/parallel_state.py | 2 + vllm/distributed/utils.py | 2 + vllm/engine/arg_utils.py | 2 + vllm/engine/async_llm_engine.py | 2 + vllm/engine/async_timeout.py | 2 + vllm/engine/llm_engine.py | 2 + vllm/engine/metrics.py | 2 + vllm/engine/metrics_types.py | 1 + vllm/engine/multiprocessing/__init__.py | 2 + vllm/engine/multiprocessing/client.py | 2 + vllm/engine/multiprocessing/engine.py | 2 + vllm/engine/output_processor/interfaces.py | 2 + vllm/engine/output_processor/multi_step.py | 2 + vllm/engine/output_processor/single_step.py | 2 + vllm/engine/output_processor/stop_checker.py | 2 + vllm/engine/output_processor/util.py | 2 + vllm/engine/protocol.py | 2 + vllm/entrypoints/api_server.py | 1 + vllm/entrypoints/chat_utils.py | 2 + vllm/entrypoints/launcher.py | 2 + vllm/entrypoints/llm.py | 2 + vllm/entrypoints/logger.py | 2 + vllm/entrypoints/openai/api_server.py | 2 + vllm/entrypoints/openai/cli_args.py | 1 + vllm/entrypoints/openai/logits_processors.py | 2 + vllm/entrypoints/openai/protocol.py | 2 + .../openai/reasoning_parsers/__init__.py | 2 + .../abs_reasoning_parsers.py | 2 + .../deepseek_r1_reasoning_parser.py | 2 + vllm/entrypoints/openai/run_batch.py | 2 + vllm/entrypoints/openai/serving_chat.py | 2 + vllm/entrypoints/openai/serving_completion.py | 2 + vllm/entrypoints/openai/serving_embedding.py | 2 + vllm/entrypoints/openai/serving_engine.py | 2 + vllm/entrypoints/openai/serving_models.py | 2 + vllm/entrypoints/openai/serving_pooling.py | 2 + vllm/entrypoints/openai/serving_rerank.py | 2 + vllm/entrypoints/openai/serving_score.py | 2 + .../openai/serving_tokenization.py | 2 + .../openai/tool_parsers/__init__.py | 2 + .../tool_parsers/abstract_tool_parser.py | 2 + .../granite_20b_fc_tool_parser.py | 2 + .../tool_parsers/granite_tool_parser.py | 2 + .../openai/tool_parsers/hermes_tool_parser.py | 2 + .../tool_parsers/internlm2_tool_parser.py | 2 + .../openai/tool_parsers/jamba_tool_parser.py | 2 + .../openai/tool_parsers/llama_tool_parser.py | 2 + .../tool_parsers/mistral_tool_parser.py | 2 + .../tool_parsers/pythonic_tool_parser.py | 2 + vllm/entrypoints/openai/tool_parsers/utils.py | 2 + vllm/entrypoints/utils.py | 2 + vllm/envs.py | 2 + vllm/executor/executor_base.py | 2 + vllm/executor/mp_distributed_executor.py | 2 + vllm/executor/msgspec_utils.py | 2 + vllm/executor/multiproc_worker_utils.py | 2 + vllm/executor/ray_distributed_executor.py | 2 + vllm/executor/ray_utils.py | 2 + vllm/executor/uniproc_executor.py | 2 + vllm/forward_context.py | 2 + vllm/inputs/__init__.py | 2 + vllm/inputs/data.py | 2 + vllm/inputs/parse.py | 2 + vllm/inputs/preprocess.py | 2 + vllm/inputs/registry.py | 2 + vllm/logger.py | 1 + vllm/logging_utils/__init__.py | 2 + vllm/logging_utils/formatter.py | 2 + vllm/logits_process.py | 2 + vllm/lora/fully_sharded_layers.py | 2 + vllm/lora/layers.py | 2 + vllm/lora/lora.py | 2 + vllm/lora/models.py | 2 + vllm/lora/ops/torch_ops/__init__.py | 2 + vllm/lora/ops/torch_ops/lora_ops.py | 2 + vllm/lora/ops/triton_ops/__init__.py | 2 + vllm/lora/ops/triton_ops/bgmv_expand.py | 1 + vllm/lora/ops/triton_ops/bgmv_expand_slice.py | 1 + vllm/lora/ops/triton_ops/bgmv_shrink.py | 1 + vllm/lora/ops/triton_ops/sgmv_expand.py | 1 + vllm/lora/ops/triton_ops/sgmv_shrink.py | 1 + vllm/lora/ops/triton_ops/utils.py | 2 + vllm/lora/peft_helper.py | 2 + vllm/lora/punica_wrapper/__init__.py | 2 + vllm/lora/punica_wrapper/punica_base.py | 1 + vllm/lora/punica_wrapper/punica_cpu.py | 2 + vllm/lora/punica_wrapper/punica_gpu.py | 1 + vllm/lora/punica_wrapper/punica_hpu.py | 2 + vllm/lora/punica_wrapper/punica_selector.py | 2 + vllm/lora/punica_wrapper/utils.py | 2 + vllm/lora/request.py | 2 + vllm/lora/utils.py | 2 + vllm/lora/worker_manager.py | 2 + vllm/model_executor/__init__.py | 2 + vllm/model_executor/custom_op.py | 2 + .../guided_decoding/__init__.py | 2 + .../guided_decoding/guided_fields.py | 2 + .../lm_format_enforcer_decoding.py | 2 + .../guided_decoding/outlines_decoding.py | 2 + .../outlines_logits_processors.py | 2 + vllm/model_executor/guided_decoding/utils.py | 2 + .../guided_decoding/xgrammar_decoding.py | 2 + vllm/model_executor/layers/activation.py | 1 + .../layers/fused_moe/__init__.py | 2 + .../layers/fused_moe/fused_marlin_moe.py | 1 + .../layers/fused_moe/fused_moe.py | 1 + vllm/model_executor/layers/fused_moe/layer.py | 2 + .../layers/fused_moe/moe_pallas.py | 2 + .../layers/fused_moe/moe_torch_iterative.py | 2 + vllm/model_executor/layers/layernorm.py | 1 + vllm/model_executor/layers/linear.py | 2 + .../model_executor/layers/logits_processor.py | 1 + .../layers/mamba/mamba_mixer.py | 2 + .../layers/mamba/ops/causal_conv1d.py | 2 + .../layers/mamba/ops/mamba_ssm.py | 2 + vllm/model_executor/layers/pooler.py | 2 + .../layers/quantization/__init__.py | 2 + .../layers/quantization/aqlm.py | 2 + .../model_executor/layers/quantization/awq.py | 2 + .../layers/quantization/awq_marlin.py | 2 + .../layers/quantization/awq_triton.py | 2 + .../layers/quantization/base_config.py | 2 + .../layers/quantization/bitsandbytes.py | 2 + .../compressed_tensors/compressed_tensors.py | 2 + .../compressed_tensors_moe.py | 2 + .../compressed_tensors/schemes/__init__.py | 2 + .../schemes/compressed_tensors_24.py | 2 + .../schemes/compressed_tensors_scheme.py | 2 + .../schemes/compressed_tensors_w4a16_24.py | 2 + .../schemes/compressed_tensors_w8a16_fp8.py | 2 + .../schemes/compressed_tensors_w8a8_fp8.py | 2 + .../schemes/compressed_tensors_w8a8_int8.py | 2 + .../schemes/compressed_tensors_wNa16.py | 2 + .../compressed_tensors/triton_scaled_mm.py | 2 + .../quantization/compressed_tensors/utils.py | 2 + .../layers/quantization/deepspeedfp.py | 2 + .../layers/quantization/experts_int8.py | 2 + .../layers/quantization/fbgemm_fp8.py | 2 + .../model_executor/layers/quantization/fp8.py | 2 + .../layers/quantization/gguf.py | 2 + .../layers/quantization/gptq.py | 2 + .../layers/quantization/gptq_marlin.py | 2 + .../layers/quantization/gptq_marlin_24.py | 2 + .../layers/quantization/hqq_marlin.py | 2 + .../layers/quantization/ipex_quant.py | 2 + .../kernels/mixed_precision/MPLinearKernel.py | 2 + .../kernels/mixed_precision/__init__.py | 2 + .../kernels/mixed_precision/exllama.py | 2 + .../kernels/mixed_precision/machete.py | 2 + .../kernels/mixed_precision/marlin.py | 2 + .../kernels/scaled_mm/ScaledMMLinearKernel.py | 2 + .../kernels/scaled_mm/__init__.py | 2 + .../quantization/kernels/scaled_mm/cutlass.py | 2 + .../quantization/kernels/scaled_mm/triton.py | 2 + .../quantization/kernels/scaled_mm/xla.py | 2 + .../layers/quantization/kv_cache.py | 2 + .../layers/quantization/marlin.py | 2 + .../layers/quantization/modelopt.py | 2 + .../layers/quantization/moe_wna16.py | 2 + .../layers/quantization/neuron_quant.py | 2 + .../model_executor/layers/quantization/qqq.py | 2 + .../layers/quantization/quark/quark.py | 2 + .../layers/quantization/quark/quark_moe.py | 2 + .../quantization/quark/schemes/__init__.py | 2 + .../quark/schemes/quark_scheme.py | 2 + .../quark/schemes/quark_w8a8_fp8.py | 2 + .../quark/schemes/quark_w8a8_int8.py | 2 + .../layers/quantization/quark/utils.py | 2 + .../layers/quantization/schema.py | 1 + .../layers/quantization/tpu_int8.py | 2 + .../layers/quantization/utils/__init__.py | 2 + .../layers/quantization/utils/fp8_utils.py | 2 + .../layers/quantization/utils/layer_utils.py | 2 + .../quantization/utils/machete_utils.py | 2 + .../layers/quantization/utils/marlin_utils.py | 2 + .../quantization/utils/marlin_utils_fp8.py | 2 + .../quantization/utils/marlin_utils_test.py | 1 + .../utils/marlin_utils_test_24.py | 1 + .../utils/marlin_utils_test_qqq.py | 2 + .../layers/quantization/utils/quant_utils.py | 1 + .../layers/quantization/utils/w8a8_utils.py | 2 + .../layers/rejection_sampler.py | 2 + vllm/model_executor/layers/resampler.py | 2 + .../model_executor/layers/rotary_embedding.py | 2 + vllm/model_executor/layers/sampler.py | 1 + .../layers/spec_decode_base_sampler.py | 2 + .../layers/typical_acceptance_sampler.py | 2 + vllm/model_executor/layers/utils.py | 1 + .../layers/vocab_parallel_embedding.py | 2 + vllm/model_executor/model_loader/__init__.py | 2 + vllm/model_executor/model_loader/loader.py | 2 + vllm/model_executor/model_loader/neuron.py | 1 + vllm/model_executor/model_loader/openvino.py | 2 + .../model_executor/model_loader/tensorizer.py | 2 + vllm/model_executor/model_loader/utils.py | 1 + .../model_loader/weight_utils.py | 1 + vllm/model_executor/models/__init__.py | 2 + vllm/model_executor/models/adapters.py | 2 + vllm/model_executor/models/arctic.py | 1 + vllm/model_executor/models/aria.py | 2 + vllm/model_executor/models/baichuan.py | 2 + vllm/model_executor/models/bart.py | 2 + vllm/model_executor/models/bert.py | 2 + vllm/model_executor/models/blip.py | 1 + vllm/model_executor/models/blip2.py | 2 + vllm/model_executor/models/bloom.py | 2 + vllm/model_executor/models/chameleon.py | 2 + vllm/model_executor/models/chatglm.py | 2 + vllm/model_executor/models/clip.py | 1 + vllm/model_executor/models/commandr.py | 2 + vllm/model_executor/models/dbrx.py | 2 + vllm/model_executor/models/decilm.py | 2 + vllm/model_executor/models/deepseek.py | 2 + vllm/model_executor/models/deepseek_v2.py | 2 + vllm/model_executor/models/deepseek_v3.py | 2 + vllm/model_executor/models/deepseek_vl2.py | 2 + vllm/model_executor/models/eagle.py | 2 + vllm/model_executor/models/exaone.py | 2 + vllm/model_executor/models/fairseq2_llama.py | 2 + vllm/model_executor/models/falcon.py | 2 + vllm/model_executor/models/florence2.py | 2 + vllm/model_executor/models/fuyu.py | 2 + vllm/model_executor/models/gemma.py | 2 + vllm/model_executor/models/gemma2.py | 2 + vllm/model_executor/models/glm.py | 1 + .../models/glm4_vision_encoder.py | 2 + vllm/model_executor/models/gpt2.py | 2 + vllm/model_executor/models/gpt_bigcode.py | 2 + vllm/model_executor/models/gpt_j.py | 2 + vllm/model_executor/models/gpt_neox.py | 2 + vllm/model_executor/models/granite.py | 2 + vllm/model_executor/models/granitemoe.py | 2 + vllm/model_executor/models/gritlm.py | 2 + vllm/model_executor/models/h2ovl.py | 2 + .../models/idefics2_vision_model.py | 2 + vllm/model_executor/models/idefics3.py | 2 + vllm/model_executor/models/interfaces.py | 2 + vllm/model_executor/models/interfaces_base.py | 2 + vllm/model_executor/models/intern_vit.py | 2 + vllm/model_executor/models/internlm2.py | 2 + vllm/model_executor/models/internlm2_ve.py | 2 + vllm/model_executor/models/internvl.py | 2 + vllm/model_executor/models/jais.py | 2 + vllm/model_executor/models/jamba.py | 1 + vllm/model_executor/models/llama.py | 2 + vllm/model_executor/models/llava.py | 2 + vllm/model_executor/models/llava_next.py | 2 + .../model_executor/models/llava_next_video.py | 2 + vllm/model_executor/models/llava_onevision.py | 2 + vllm/model_executor/models/mamba.py | 1 + vllm/model_executor/models/mamba_cache.py | 2 + vllm/model_executor/models/medusa.py | 2 + vllm/model_executor/models/minicpm.py | 2 + vllm/model_executor/models/minicpm3.py | 2 + vllm/model_executor/models/minicpmo.py | 2 + vllm/model_executor/models/minicpmv.py | 2 + vllm/model_executor/models/mixtral.py | 2 + vllm/model_executor/models/mixtral_quant.py | 2 + vllm/model_executor/models/mllama.py | 2 + vllm/model_executor/models/mlp_speculator.py | 2 + vllm/model_executor/models/module_mapping.py | 2 + vllm/model_executor/models/molmo.py | 2 + vllm/model_executor/models/mpt.py | 2 + vllm/model_executor/models/nemotron.py | 2 + vllm/model_executor/models/nvlm_d.py | 2 + vllm/model_executor/models/olmo.py | 2 + vllm/model_executor/models/olmo2.py | 2 + vllm/model_executor/models/olmoe.py | 2 + vllm/model_executor/models/opt.py | 2 + vllm/model_executor/models/orion.py | 2 + vllm/model_executor/models/paligemma.py | 2 + vllm/model_executor/models/persimmon.py | 2 + vllm/model_executor/models/phi.py | 2 + vllm/model_executor/models/phi3.py | 2 + vllm/model_executor/models/phi3_small.py | 2 + vllm/model_executor/models/phi3v.py | 2 + vllm/model_executor/models/phimoe.py | 2 + vllm/model_executor/models/pixtral.py | 2 + vllm/model_executor/models/qwen.py | 2 + vllm/model_executor/models/qwen2.py | 2 + vllm/model_executor/models/qwen2_audio.py | 2 + vllm/model_executor/models/qwen2_moe.py | 2 + vllm/model_executor/models/qwen2_rm.py | 2 + vllm/model_executor/models/qwen2_vl.py | 2 + vllm/model_executor/models/registry.py | 1 + vllm/model_executor/models/roberta.py | 2 + vllm/model_executor/models/siglip.py | 1 + vllm/model_executor/models/solar.py | 2 + vllm/model_executor/models/stablelm.py | 2 + vllm/model_executor/models/starcoder2.py | 2 + vllm/model_executor/models/telechat2.py | 2 + vllm/model_executor/models/ultravox.py | 2 + vllm/model_executor/models/utils.py | 2 + vllm/model_executor/models/vision.py | 2 + vllm/model_executor/models/whisper.py | 2 + vllm/model_executor/parameter.py | 2 + vllm/model_executor/pooling_metadata.py | 2 + vllm/model_executor/sampling_metadata.py | 2 + vllm/model_executor/utils.py | 1 + vllm/multimodal/__init__.py | 2 + vllm/multimodal/audio.py | 2 + vllm/multimodal/base.py | 2 + vllm/multimodal/hasher.py | 2 + vllm/multimodal/image.py | 2 + vllm/multimodal/inputs.py | 2 + vllm/multimodal/parse.py | 2 + vllm/multimodal/processing.py | 2 + vllm/multimodal/profiling.py | 2 + vllm/multimodal/registry.py | 2 + vllm/multimodal/utils.py | 2 + vllm/multimodal/video.py | 2 + vllm/outputs.py | 2 + vllm/platforms/__init__.py | 2 + vllm/platforms/cpu.py | 2 + vllm/platforms/cuda.py | 1 + vllm/platforms/hpu.py | 2 + vllm/platforms/interface.py | 2 + vllm/platforms/neuron.py | 2 + vllm/platforms/openvino.py | 2 + vllm/platforms/rocm.py | 2 + vllm/platforms/tpu.py | 2 + vllm/platforms/xpu.py | 2 + vllm/plugins/__init__.py | 2 + vllm/pooling_params.py | 2 + vllm/profiler/__init__.py | 2 + vllm/profiler/layerwise_profile.py | 2 + vllm/profiler/utils.py | 2 + vllm/prompt_adapter/layers.py | 2 + vllm/prompt_adapter/models.py | 2 + vllm/prompt_adapter/request.py | 2 + vllm/prompt_adapter/utils.py | 2 + vllm/prompt_adapter/worker_manager.py | 2 + vllm/sampling_params.py | 1 + vllm/scalar_type.py | 2 + vllm/scripts.py | 2 + vllm/sequence.py | 1 + vllm/spec_decode/batch_expansion.py | 2 + vllm/spec_decode/draft_model_runner.py | 2 + vllm/spec_decode/interfaces.py | 2 + vllm/spec_decode/medusa_worker.py | 2 + vllm/spec_decode/metrics.py | 2 + vllm/spec_decode/mlp_speculator_worker.py | 2 + vllm/spec_decode/mqa_scorer.py | 2 + vllm/spec_decode/multi_step_worker.py | 2 + vllm/spec_decode/ngram_worker.py | 2 + vllm/spec_decode/proposer_worker_base.py | 2 + .../spec_decode/smaller_tp_proposer_worker.py | 2 + vllm/spec_decode/spec_decode_worker.py | 2 + vllm/spec_decode/target_model_runner.py | 2 + vllm/spec_decode/top1_proposer.py | 2 + vllm/spec_decode/util.py | 2 + vllm/tracing.py | 2 + vllm/transformers_utils/__init__.py | 2 + vllm/transformers_utils/config.py | 2 + vllm/transformers_utils/configs/__init__.py | 2 + vllm/transformers_utils/configs/arctic.py | 2 + vllm/transformers_utils/configs/chatglm.py | 2 + vllm/transformers_utils/configs/cohere2.py | 2 + vllm/transformers_utils/configs/dbrx.py | 2 + .../configs/deepseek_vl2.py | 2 + vllm/transformers_utils/configs/eagle.py | 2 + vllm/transformers_utils/configs/exaone.py | 2 + vllm/transformers_utils/configs/falcon.py | 2 + vllm/transformers_utils/configs/h2ovl.py | 2 + vllm/transformers_utils/configs/internvl.py | 2 + vllm/transformers_utils/configs/jais.py | 2 + vllm/transformers_utils/configs/medusa.py | 2 + vllm/transformers_utils/configs/mllama.py | 2 + .../configs/mlp_speculator.py | 2 + vllm/transformers_utils/configs/mpt.py | 2 + vllm/transformers_utils/configs/nemotron.py | 2 + vllm/transformers_utils/configs/nvlm_d.py | 2 + vllm/transformers_utils/configs/olmo2.py | 2 + vllm/transformers_utils/configs/solar.py | 2 + vllm/transformers_utils/configs/telechat2.py | 2 + vllm/transformers_utils/configs/ultravox.py | 2 + vllm/transformers_utils/detokenizer.py | 2 + vllm/transformers_utils/detokenizer_utils.py | 2 + vllm/transformers_utils/processor.py | 2 + .../transformers_utils/processors/__init__.py | 2 + .../processors/deepseek_vl2.py | 2 + vllm/transformers_utils/s3_utils.py | 2 + vllm/transformers_utils/tokenizer.py | 2 + .../tokenizer_group/__init__.py | 2 + .../tokenizer_group/base_tokenizer_group.py | 2 + .../tokenizer_group/ray_tokenizer_group.py | 2 + .../tokenizer_group/tokenizer_group.py | 2 + .../transformers_utils/tokenizers/__init__.py | 2 + vllm/transformers_utils/tokenizers/mistral.py | 2 + vllm/transformers_utils/utils.py | 2 + vllm/triton_utils/__init__.py | 2 + vllm/triton_utils/custom_cache_manager.py | 2 + vllm/triton_utils/importing.py | 2 + vllm/usage/usage_lib.py | 2 + vllm/utils.py | 2 + vllm/v1/attention/backends/flash_attn.py | 1 + vllm/v1/core/encoder_cache_manager.py | 2 + vllm/v1/core/kv_cache_manager.py | 2 + vllm/v1/core/kv_cache_utils.py | 1 + vllm/v1/core/scheduler.py | 2 + vllm/v1/engine/__init__.py | 2 + vllm/v1/engine/async_llm.py | 2 + vllm/v1/engine/core.py | 2 + vllm/v1/engine/core_client.py | 2 + vllm/v1/engine/detokenizer.py | 2 + vllm/v1/engine/llm_engine.py | 2 + vllm/v1/engine/mm_input_mapper.py | 2 + vllm/v1/engine/output_processor.py | 2 + vllm/v1/engine/processor.py | 2 + vllm/v1/executor/abstract.py | 2 + vllm/v1/executor/multiproc_executor.py | 2 + vllm/v1/kv_cache_interface.py | 2 + vllm/v1/metrics/loggers.py | 2 + vllm/v1/metrics/stats.py | 2 + vllm/v1/outputs.py | 2 + vllm/v1/request.py | 2 + vllm/v1/sample/metadata.py | 2 + vllm/v1/sample/ops/penalties.py | 2 + vllm/v1/sample/ops/topk_topp_sampler.py | 2 + vllm/v1/sample/sampler.py | 1 + vllm/v1/serial_utils.py | 2 + vllm/v1/stats/common.py | 2 + vllm/v1/utils.py | 2 + vllm/v1/worker/block_table.py | 2 + vllm/v1/worker/gpu_input_batch.py | 2 + vllm/v1/worker/gpu_model_runner.py | 2 + vllm/v1/worker/gpu_worker.py | 1 + vllm/version.py | 2 + vllm/worker/cache_engine.py | 1 + vllm/worker/cpu_enc_dec_model_runner.py | 2 + vllm/worker/cpu_model_runner.py | 2 + vllm/worker/cpu_pooling_model_runner.py | 2 + vllm/worker/cpu_worker.py | 1 + vllm/worker/enc_dec_model_runner.py | 2 + vllm/worker/hpu_model_runner.py | 2 + vllm/worker/hpu_worker.py | 2 + vllm/worker/model_runner.py | 2 + vllm/worker/model_runner_base.py | 2 + vllm/worker/multi_step_model_runner.py | 2 + vllm/worker/multi_step_tpu_worker.py | 2 + vllm/worker/multi_step_worker.py | 2 + vllm/worker/neuron_model_runner.py | 2 + vllm/worker/neuron_worker.py | 1 + vllm/worker/openvino_model_runner.py | 2 + vllm/worker/openvino_worker.py | 1 + vllm/worker/pooling_model_runner.py | 2 + vllm/worker/tpu_model_runner.py | 2 + vllm/worker/tpu_worker.py | 2 + vllm/worker/utils.py | 1 + vllm/worker/worker.py | 1 + vllm/worker/worker_base.py | 2 + vllm/worker/xpu_model_runner.py | 2 + vllm/worker/xpu_worker.py | 1 + 1012 files changed, 1884 insertions(+), 2 deletions(-) create mode 100644 tools/check_spdx_header.py diff --git a/.buildkite/check-wheel-size.py b/.buildkite/check-wheel-size.py index e29eb78a9..2e4aecdd3 100644 --- a/.buildkite/check-wheel-size.py +++ b/.buildkite/check-wheel-size.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import os import sys import zipfile diff --git a/.buildkite/generate_index.py b/.buildkite/generate_index.py index 8350e2705..36e1b6c01 100644 --- a/.buildkite/generate_index.py +++ b/.buildkite/generate_index.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import argparse import os diff --git a/.buildkite/lm-eval-harness/test_lm_eval_correctness.py b/.buildkite/lm-eval-harness/test_lm_eval_correctness.py index afc935c1a..96e57dfd0 100644 --- a/.buildkite/lm-eval-harness/test_lm_eval_correctness.py +++ b/.buildkite/lm-eval-harness/test_lm_eval_correctness.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """ LM eval harness on model to compare vs HF baseline computed offline. Configs are found in configs/$MODEL.yaml diff --git a/.buildkite/nightly-benchmarks/scripts/convert-results-json-to-markdown.py b/.buildkite/nightly-benchmarks/scripts/convert-results-json-to-markdown.py index 9d3646e2f..e031686c7 100644 --- a/.buildkite/nightly-benchmarks/scripts/convert-results-json-to-markdown.py +++ b/.buildkite/nightly-benchmarks/scripts/convert-results-json-to-markdown.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import json import os from pathlib import Path diff --git a/.buildkite/nightly-benchmarks/scripts/download-tokenizer.py b/.buildkite/nightly-benchmarks/scripts/download-tokenizer.py index 68ac5909e..5e17b79d2 100644 --- a/.buildkite/nightly-benchmarks/scripts/download-tokenizer.py +++ b/.buildkite/nightly-benchmarks/scripts/download-tokenizer.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import argparse from transformers import AutoTokenizer diff --git a/.buildkite/nightly-benchmarks/scripts/generate-nightly-markdown.py b/.buildkite/nightly-benchmarks/scripts/generate-nightly-markdown.py index 052060c57..0ff95a091 100644 --- a/.buildkite/nightly-benchmarks/scripts/generate-nightly-markdown.py +++ b/.buildkite/nightly-benchmarks/scripts/generate-nightly-markdown.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import argparse import json from pathlib import Path diff --git a/.buildkite/nightly-benchmarks/scripts/get-lmdeploy-modelname.py b/.buildkite/nightly-benchmarks/scripts/get-lmdeploy-modelname.py index 18bcc3a87..e5f179a0f 100644 --- a/.buildkite/nightly-benchmarks/scripts/get-lmdeploy-modelname.py +++ b/.buildkite/nightly-benchmarks/scripts/get-lmdeploy-modelname.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from lmdeploy.serve.openai.api_client import APIClient api_client = APIClient("http://localhost:8000") diff --git a/.buildkite/nightly-benchmarks/scripts/summary-nightly-results.py b/.buildkite/nightly-benchmarks/scripts/summary-nightly-results.py index 92d6fad73..62ee5e10b 100644 --- a/.buildkite/nightly-benchmarks/scripts/summary-nightly-results.py +++ b/.buildkite/nightly-benchmarks/scripts/summary-nightly-results.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import datetime import json import os diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml index ae518e190..4568efcbb 100644 --- a/.pre-commit-config.yaml +++ b/.pre-commit-config.yaml @@ -97,10 +97,14 @@ repos: language: system verbose: true stages: [commit-msg] + - id: check-spdx-header + name: Check SPDX headers + entry: python tools/check_spdx_header.py + language: python + types: [python] - id: suggestion name: Suggestion entry: bash -c 'echo "To bypass pre-commit hooks, add --no-verify to git commit."' language: system verbose: true pass_filenames: false - diff --git a/benchmarks/backend_request_func.py b/benchmarks/backend_request_func.py index 0612e8778..364b087b8 100644 --- a/benchmarks/backend_request_func.py +++ b/benchmarks/backend_request_func.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import json import os import sys diff --git a/benchmarks/benchmark_guided.py b/benchmarks/benchmark_guided.py index 1a0e62598..2b41834ba 100644 --- a/benchmarks/benchmark_guided.py +++ b/benchmarks/benchmark_guided.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Benchmark guided decoding throughput.""" import argparse import dataclasses diff --git a/benchmarks/benchmark_latency.py b/benchmarks/benchmark_latency.py index 77c4f6aa9..896312945 100644 --- a/benchmarks/benchmark_latency.py +++ b/benchmarks/benchmark_latency.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Benchmark the latency of processing a single batch of requests.""" import argparse import dataclasses diff --git a/benchmarks/benchmark_long_document_qa_throughput.py b/benchmarks/benchmark_long_document_qa_throughput.py index 0b8fba381..21480578e 100644 --- a/benchmarks/benchmark_long_document_qa_throughput.py +++ b/benchmarks/benchmark_long_document_qa_throughput.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """ Offline benchmark to test the long document QA throughput. diff --git a/benchmarks/benchmark_prefix_caching.py b/benchmarks/benchmark_prefix_caching.py index 3ab421a89..23822856b 100644 --- a/benchmarks/benchmark_prefix_caching.py +++ b/benchmarks/benchmark_prefix_caching.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """ Benchmark the efficiency of prefix caching. diff --git a/benchmarks/benchmark_prioritization.py b/benchmarks/benchmark_prioritization.py index e0c9e6a6d..a32065e4e 100644 --- a/benchmarks/benchmark_prioritization.py +++ b/benchmarks/benchmark_prioritization.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Benchmark offline prioritization.""" import argparse import dataclasses diff --git a/benchmarks/benchmark_serving.py b/benchmarks/benchmark_serving.py index 8b3212831..e934d228f 100644 --- a/benchmarks/benchmark_serving.py +++ b/benchmarks/benchmark_serving.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 r"""Benchmark online serving throughput. On the server side, run one of the following commands: diff --git a/benchmarks/benchmark_serving_guided.py b/benchmarks/benchmark_serving_guided.py index 4435d87e1..561e500d8 100644 --- a/benchmarks/benchmark_serving_guided.py +++ b/benchmarks/benchmark_serving_guided.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 r"""Benchmark online serving throughput with guided decoding. On the server side, run one of the following commands: diff --git a/benchmarks/benchmark_throughput.py b/benchmarks/benchmark_throughput.py index c1b10b3cf..658eab6a2 100644 --- a/benchmarks/benchmark_throughput.py +++ b/benchmarks/benchmark_throughput.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Benchmark offline inference throughput.""" import argparse import dataclasses diff --git a/benchmarks/cutlass_benchmarks/sparse_benchmarks.py b/benchmarks/cutlass_benchmarks/sparse_benchmarks.py index 3d1c5e392..468a1b286 100644 --- a/benchmarks/cutlass_benchmarks/sparse_benchmarks.py +++ b/benchmarks/cutlass_benchmarks/sparse_benchmarks.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import argparse import copy import itertools diff --git a/benchmarks/cutlass_benchmarks/utils.py b/benchmarks/cutlass_benchmarks/utils.py index ef06fcd66..bab377800 100644 --- a/benchmarks/cutlass_benchmarks/utils.py +++ b/benchmarks/cutlass_benchmarks/utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Cutlass bench utils from typing import Iterable, Tuple diff --git a/benchmarks/cutlass_benchmarks/w8a8_benchmarks.py b/benchmarks/cutlass_benchmarks/w8a8_benchmarks.py index b87496ca3..6552b62da 100644 --- a/benchmarks/cutlass_benchmarks/w8a8_benchmarks.py +++ b/benchmarks/cutlass_benchmarks/w8a8_benchmarks.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import argparse import copy import itertools diff --git a/benchmarks/cutlass_benchmarks/weight_shapes.py b/benchmarks/cutlass_benchmarks/weight_shapes.py index d58fb0bf8..3d1121df4 100644 --- a/benchmarks/cutlass_benchmarks/weight_shapes.py +++ b/benchmarks/cutlass_benchmarks/weight_shapes.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Weight Shapes are in the format # ([K, N], TP_SPLIT_DIM) # Example: diff --git a/benchmarks/disagg_benchmarks/disagg_prefill_proxy_server.py b/benchmarks/disagg_benchmarks/disagg_prefill_proxy_server.py index 4058b1c0a..980e68668 100644 --- a/benchmarks/disagg_benchmarks/disagg_prefill_proxy_server.py +++ b/benchmarks/disagg_benchmarks/disagg_prefill_proxy_server.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import os import aiohttp diff --git a/benchmarks/disagg_benchmarks/round_robin_proxy.py b/benchmarks/disagg_benchmarks/round_robin_proxy.py index 6eb5f6398..c2ad4916b 100644 --- a/benchmarks/disagg_benchmarks/round_robin_proxy.py +++ b/benchmarks/disagg_benchmarks/round_robin_proxy.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import asyncio import itertools diff --git a/benchmarks/disagg_benchmarks/visualize_benchmark_results.py b/benchmarks/disagg_benchmarks/visualize_benchmark_results.py index e59d8bb0e..a7b4b9e8b 100644 --- a/benchmarks/disagg_benchmarks/visualize_benchmark_results.py +++ b/benchmarks/disagg_benchmarks/visualize_benchmark_results.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import json import matplotlib.pyplot as plt diff --git a/benchmarks/fused_kernels/layernorm_rms_benchmarks.py b/benchmarks/fused_kernels/layernorm_rms_benchmarks.py index ef91f9f8e..c56cc7438 100644 --- a/benchmarks/fused_kernels/layernorm_rms_benchmarks.py +++ b/benchmarks/fused_kernels/layernorm_rms_benchmarks.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import pickle as pkl import time from dataclasses import dataclass diff --git a/benchmarks/kernels/benchmark_aqlm.py b/benchmarks/kernels/benchmark_aqlm.py index 601c4ea43..8d20b9156 100644 --- a/benchmarks/kernels/benchmark_aqlm.py +++ b/benchmarks/kernels/benchmark_aqlm.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import os import sys from typing import Optional diff --git a/benchmarks/kernels/benchmark_layernorm.py b/benchmarks/kernels/benchmark_layernorm.py index 7acea6087..d265c91bf 100644 --- a/benchmarks/kernels/benchmark_layernorm.py +++ b/benchmarks/kernels/benchmark_layernorm.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import time import torch diff --git a/benchmarks/kernels/benchmark_lora.py b/benchmarks/kernels/benchmark_lora.py index e1f613e1d..ecde8fbaa 100644 --- a/benchmarks/kernels/benchmark_lora.py +++ b/benchmarks/kernels/benchmark_lora.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import argparse import copy import json diff --git a/benchmarks/kernels/benchmark_machete.py b/benchmarks/kernels/benchmark_machete.py index 46bab74ae..0301fee1a 100644 --- a/benchmarks/kernels/benchmark_machete.py +++ b/benchmarks/kernels/benchmark_machete.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import argparse import copy import itertools diff --git a/benchmarks/kernels/benchmark_marlin.py b/benchmarks/kernels/benchmark_marlin.py index 8fb44e3a3..c22e66c0b 100644 --- a/benchmarks/kernels/benchmark_marlin.py +++ b/benchmarks/kernels/benchmark_marlin.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List import torch diff --git a/benchmarks/kernels/benchmark_moe.py b/benchmarks/kernels/benchmark_moe.py index 068830f02..a4a45c9cb 100644 --- a/benchmarks/kernels/benchmark_moe.py +++ b/benchmarks/kernels/benchmark_moe.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import argparse import time from datetime import datetime diff --git a/benchmarks/kernels/benchmark_paged_attention.py b/benchmarks/kernels/benchmark_paged_attention.py index 219013a38..daedaadb1 100644 --- a/benchmarks/kernels/benchmark_paged_attention.py +++ b/benchmarks/kernels/benchmark_paged_attention.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import random import time from typing import List, Optional diff --git a/benchmarks/kernels/benchmark_quant.py b/benchmarks/kernels/benchmark_quant.py index 1d6248344..0ddea9390 100644 --- a/benchmarks/kernels/benchmark_quant.py +++ b/benchmarks/kernels/benchmark_quant.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import time import torch diff --git a/benchmarks/kernels/benchmark_rmsnorm.py b/benchmarks/kernels/benchmark_rmsnorm.py index baa5de0ff..dba153742 100644 --- a/benchmarks/kernels/benchmark_rmsnorm.py +++ b/benchmarks/kernels/benchmark_rmsnorm.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import itertools from typing import Optional, Tuple, Union diff --git a/benchmarks/kernels/benchmark_rope.py b/benchmarks/kernels/benchmark_rope.py index 250d50516..8ee0212a0 100644 --- a/benchmarks/kernels/benchmark_rope.py +++ b/benchmarks/kernels/benchmark_rope.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from itertools import accumulate from typing import List, Optional diff --git a/benchmarks/kernels/benchmark_shapes.py b/benchmarks/kernels/benchmark_shapes.py index 4eeeca35a..c375e61e4 100644 --- a/benchmarks/kernels/benchmark_shapes.py +++ b/benchmarks/kernels/benchmark_shapes.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + WEIGHT_SHAPES = { "ideal": [[4 * 256 * 32, 256 * 32]], "mistralai/Mistral-7B-v0.1/TP1": [ diff --git a/benchmarks/kernels/graph_machete_bench.py b/benchmarks/kernels/graph_machete_bench.py index 7d0bd8415..01d97d63d 100644 --- a/benchmarks/kernels/graph_machete_bench.py +++ b/benchmarks/kernels/graph_machete_bench.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import math import pickle import re diff --git a/benchmarks/kernels/utils.py b/benchmarks/kernels/utils.py index fee877b6f..728170748 100644 --- a/benchmarks/kernels/utils.py +++ b/benchmarks/kernels/utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import dataclasses from typing import Any, Callable, Iterable, Optional diff --git a/benchmarks/kernels/weight_shapes.py b/benchmarks/kernels/weight_shapes.py index 51f24f3ba..89b05d588 100644 --- a/benchmarks/kernels/weight_shapes.py +++ b/benchmarks/kernels/weight_shapes.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Weight Shapes are in the format # ([K, N], TP_SPLIT_DIM) # Example: diff --git a/benchmarks/overheads/benchmark_hashing.py b/benchmarks/overheads/benchmark_hashing.py index d16d6f9fb..5f94552e9 100644 --- a/benchmarks/overheads/benchmark_hashing.py +++ b/benchmarks/overheads/benchmark_hashing.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import cProfile import pstats diff --git a/cmake/hipify.py b/cmake/hipify.py index 340e41c81..2e0c8a172 100755 --- a/cmake/hipify.py +++ b/cmake/hipify.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + #!/usr/bin/env python3 # diff --git a/collect_env.py b/collect_env.py index 254c19b19..0ec9d4cae 100644 --- a/collect_env.py +++ b/collect_env.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # ruff: noqa # code borrowed from https://github.com/pytorch/pytorch/blob/main/torch/utils/collect_env.py diff --git a/csrc/cutlass_extensions/vllm_cutlass_library_extension.py b/csrc/cutlass_extensions/vllm_cutlass_library_extension.py index b401736c9..d5a5e2ef8 100644 --- a/csrc/cutlass_extensions/vllm_cutlass_library_extension.py +++ b/csrc/cutlass_extensions/vllm_cutlass_library_extension.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import enum from typing import Dict, Union diff --git a/csrc/quantization/machete/generate.py b/csrc/quantization/machete/generate.py index a9b5ddf4c..02e59fe28 100644 --- a/csrc/quantization/machete/generate.py +++ b/csrc/quantization/machete/generate.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import itertools import math import os diff --git a/docs/source/conf.py b/docs/source/conf.py index 6b0a1dad1..ea3b56e02 100644 --- a/docs/source/conf.py +++ b/docs/source/conf.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Configuration file for the Sphinx documentation builder. # # This file only contains a selection of the most common options. For a full diff --git a/docs/source/generate_examples.py b/docs/source/generate_examples.py index ac592e223..9d4de18a3 100644 --- a/docs/source/generate_examples.py +++ b/docs/source/generate_examples.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import itertools import re from dataclasses import dataclass, field diff --git a/examples/offline_inference/aqlm_example.py b/examples/offline_inference/aqlm_example.py index 40f9a21ec..e8db3811f 100644 --- a/examples/offline_inference/aqlm_example.py +++ b/examples/offline_inference/aqlm_example.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from vllm import LLM, SamplingParams from vllm.utils import FlexibleArgumentParser diff --git a/examples/offline_inference/arctic.py b/examples/offline_inference/arctic.py index 1fec3c99e..90c88446c 100644 --- a/examples/offline_inference/arctic.py +++ b/examples/offline_inference/arctic.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from vllm import LLM, SamplingParams # Sample prompts. diff --git a/examples/offline_inference/audio_language.py b/examples/offline_inference/audio_language.py index 5952ec13e..707ca9f87 100644 --- a/examples/offline_inference/audio_language.py +++ b/examples/offline_inference/audio_language.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """ This example shows how to use vLLM for running offline inference with the correct prompt format on audio language models. diff --git a/examples/offline_inference/basic.py b/examples/offline_inference/basic.py index 23cc6e853..a6e96c0bb 100644 --- a/examples/offline_inference/basic.py +++ b/examples/offline_inference/basic.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from vllm import LLM, SamplingParams # Sample prompts. diff --git a/examples/offline_inference/basic_with_model_default_sampling.py b/examples/offline_inference/basic_with_model_default_sampling.py index 346bb80b1..80de9428f 100644 --- a/examples/offline_inference/basic_with_model_default_sampling.py +++ b/examples/offline_inference/basic_with_model_default_sampling.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from vllm import LLM # Sample prompts. diff --git a/examples/offline_inference/chat.py b/examples/offline_inference/chat.py index 8814f4d7b..dbc710cc8 100644 --- a/examples/offline_inference/chat.py +++ b/examples/offline_inference/chat.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from vllm import LLM, SamplingParams llm = LLM(model="meta-llama/Meta-Llama-3-8B-Instruct") diff --git a/examples/offline_inference/chat_with_tools.py b/examples/offline_inference/chat_with_tools.py index e69a6c067..15519bfed 100644 --- a/examples/offline_inference/chat_with_tools.py +++ b/examples/offline_inference/chat_with_tools.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # ruff: noqa import json import random diff --git a/examples/offline_inference/classification.py b/examples/offline_inference/classification.py index de539b639..4a364aeb8 100644 --- a/examples/offline_inference/classification.py +++ b/examples/offline_inference/classification.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from vllm import LLM # Sample prompts. diff --git a/examples/offline_inference/cli.py b/examples/offline_inference/cli.py index 391ac6b9b..bc6833b3f 100644 --- a/examples/offline_inference/cli.py +++ b/examples/offline_inference/cli.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from dataclasses import asdict from vllm import LLM, SamplingParams diff --git a/examples/offline_inference/cpu_offload.py b/examples/offline_inference/cpu_offload.py index b152e5bc3..5511eb738 100644 --- a/examples/offline_inference/cpu_offload.py +++ b/examples/offline_inference/cpu_offload.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from vllm import LLM, SamplingParams # Sample prompts. diff --git a/examples/offline_inference/distributed.py b/examples/offline_inference/distributed.py index 677127844..a2df41d4c 100644 --- a/examples/offline_inference/distributed.py +++ b/examples/offline_inference/distributed.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """ This example shows how to use Ray Data for running offline batch inference distributively on a multi-nodes cluster. diff --git a/examples/offline_inference/embedding.py b/examples/offline_inference/embedding.py index 58d004313..f9399329d 100644 --- a/examples/offline_inference/embedding.py +++ b/examples/offline_inference/embedding.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from vllm import LLM # Sample prompts. diff --git a/examples/offline_inference/encoder_decoder.py b/examples/offline_inference/encoder_decoder.py index 0f266d791..8765d1812 100644 --- a/examples/offline_inference/encoder_decoder.py +++ b/examples/offline_inference/encoder_decoder.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 ''' Demonstrate prompting of text-to-text encoder/decoder models, specifically BART diff --git a/examples/offline_inference/florence2_inference.py b/examples/offline_inference/florence2_inference.py index c24096e90..58610b0fd 100644 --- a/examples/offline_inference/florence2_inference.py +++ b/examples/offline_inference/florence2_inference.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 ''' Demonstrate prompting of text-to-text encoder/decoder models, specifically Florence-2 diff --git a/examples/offline_inference/gguf_inference.py b/examples/offline_inference/gguf_inference.py index aa05c4c0b..0447e74e0 100644 --- a/examples/offline_inference/gguf_inference.py +++ b/examples/offline_inference/gguf_inference.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from huggingface_hub import hf_hub_download from vllm import LLM, SamplingParams diff --git a/examples/offline_inference/llm_engine_example.py b/examples/offline_inference/llm_engine_example.py index 60d894aae..501034c1c 100644 --- a/examples/offline_inference/llm_engine_example.py +++ b/examples/offline_inference/llm_engine_example.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import argparse from typing import List, Tuple diff --git a/examples/offline_inference/lora_with_quantization_inference.py b/examples/offline_inference/lora_with_quantization_inference.py index 0c454ea50..de0734c1a 100644 --- a/examples/offline_inference/lora_with_quantization_inference.py +++ b/examples/offline_inference/lora_with_quantization_inference.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """ This example shows how to use LoRA with different quantization techniques for offline inference. diff --git a/examples/offline_inference/mlpspeculator.py b/examples/offline_inference/mlpspeculator.py index 8f0eb65e4..10d9de8cb 100644 --- a/examples/offline_inference/mlpspeculator.py +++ b/examples/offline_inference/mlpspeculator.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import gc import time from typing import List diff --git a/examples/offline_inference/multilora_inference.py b/examples/offline_inference/multilora_inference.py index 043220d97..630fd1bf8 100644 --- a/examples/offline_inference/multilora_inference.py +++ b/examples/offline_inference/multilora_inference.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """ This example shows how to use the multi-LoRA functionality for offline inference. diff --git a/examples/offline_inference/neuron.py b/examples/offline_inference/neuron.py index f098c8e5f..517d1bfce 100644 --- a/examples/offline_inference/neuron.py +++ b/examples/offline_inference/neuron.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from vllm import LLM, SamplingParams # Sample prompts. diff --git a/examples/offline_inference/neuron_int8_quantization.py b/examples/offline_inference/neuron_int8_quantization.py index 8ec17e340..c899a01a0 100644 --- a/examples/offline_inference/neuron_int8_quantization.py +++ b/examples/offline_inference/neuron_int8_quantization.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import os from vllm import LLM, SamplingParams diff --git a/examples/offline_inference/pixtral.py b/examples/offline_inference/pixtral.py index c12ff7021..760de1145 100644 --- a/examples/offline_inference/pixtral.py +++ b/examples/offline_inference/pixtral.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # ruff: noqa import argparse diff --git a/examples/offline_inference/prefix_caching.py b/examples/offline_inference/prefix_caching.py index 67b755a15..4c326c417 100644 --- a/examples/offline_inference/prefix_caching.py +++ b/examples/offline_inference/prefix_caching.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from vllm import LLM, SamplingParams from vllm.distributed import cleanup_dist_env_and_memory diff --git a/examples/offline_inference/profiling.py b/examples/offline_inference/profiling.py index 8a94b5c2a..c2e072fdd 100644 --- a/examples/offline_inference/profiling.py +++ b/examples/offline_inference/profiling.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import inspect import json import os diff --git a/examples/offline_inference/profiling_tpu/profiling.py b/examples/offline_inference/profiling_tpu/profiling.py index d7423e6c6..b1fe829b3 100644 --- a/examples/offline_inference/profiling_tpu/profiling.py +++ b/examples/offline_inference/profiling_tpu/profiling.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import argparse import dataclasses import os diff --git a/examples/offline_inference/rlhf.py b/examples/offline_inference/rlhf.py index 5c4918008..5000251c0 100644 --- a/examples/offline_inference/rlhf.py +++ b/examples/offline_inference/rlhf.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """ a simple demonstration of RLHF with vLLM, inspired by the OpenRLHF framework https://github.com/OpenRLHF/OpenRLHF . diff --git a/examples/offline_inference/save_sharded_state.py b/examples/offline_inference/save_sharded_state.py index 4207f8922..863276432 100644 --- a/examples/offline_inference/save_sharded_state.py +++ b/examples/offline_inference/save_sharded_state.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """ Saves each worker's model state dict directly to a checkpoint, which enables a fast load path for large tensor-parallel models where each worker only needs to diff --git a/examples/offline_inference/scoring.py b/examples/offline_inference/scoring.py index 5da9e7109..7daa82b82 100644 --- a/examples/offline_inference/scoring.py +++ b/examples/offline_inference/scoring.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from vllm import LLM # Sample prompts. diff --git a/examples/offline_inference/simple_profiling.py b/examples/offline_inference/simple_profiling.py index abcfa8e8f..b45954b3b 100644 --- a/examples/offline_inference/simple_profiling.py +++ b/examples/offline_inference/simple_profiling.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import os import time diff --git a/examples/offline_inference/structured_outputs.py b/examples/offline_inference/structured_outputs.py index 00d864606..38ffd7fb9 100644 --- a/examples/offline_inference/structured_outputs.py +++ b/examples/offline_inference/structured_outputs.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from enum import Enum from pydantic import BaseModel diff --git a/examples/offline_inference/torchrun_example.py b/examples/offline_inference/torchrun_example.py index b6de73eb7..35df60115 100644 --- a/examples/offline_inference/torchrun_example.py +++ b/examples/offline_inference/torchrun_example.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """ experimental support for tensor-parallel inference with torchrun, see https://github.com/vllm-project/vllm/issues/11400 for diff --git a/examples/offline_inference/tpu.py b/examples/offline_inference/tpu.py index 251629b80..bd0e98462 100644 --- a/examples/offline_inference/tpu.py +++ b/examples/offline_inference/tpu.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from vllm import LLM, SamplingParams prompts = [ diff --git a/examples/offline_inference/vision_language.py b/examples/offline_inference/vision_language.py index 38c2b13d3..65940b6ad 100644 --- a/examples/offline_inference/vision_language.py +++ b/examples/offline_inference/vision_language.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """ This example shows how to use vLLM for running offline inference with the correct prompt format on vision language models for text generation. diff --git a/examples/offline_inference/vision_language_embedding.py b/examples/offline_inference/vision_language_embedding.py index 4ce3d496b..3075fbbfa 100644 --- a/examples/offline_inference/vision_language_embedding.py +++ b/examples/offline_inference/vision_language_embedding.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """ This example shows how to use vLLM for running offline inference with the correct prompt format on vision language models for multimodal embedding. diff --git a/examples/offline_inference/vision_language_multi_image.py b/examples/offline_inference/vision_language_multi_image.py index 43c44fa86..601ac96e1 100644 --- a/examples/offline_inference/vision_language_multi_image.py +++ b/examples/offline_inference/vision_language_multi_image.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """ This example shows how to use vLLM for running offline inference with multi-image input on vision language models for text generation, diff --git a/examples/offline_inference/whisper.py b/examples/offline_inference/whisper.py index 087ad4376..59c119a77 100644 --- a/examples/offline_inference/whisper.py +++ b/examples/offline_inference/whisper.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import time from vllm import LLM, SamplingParams diff --git a/examples/online_serving/api_client.py b/examples/online_serving/api_client.py index 49a085feb..623e0d59a 100644 --- a/examples/online_serving/api_client.py +++ b/examples/online_serving/api_client.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Example Python client for `vllm.entrypoints.api_server` NOTE: The API server is used only for demonstration and simple performance benchmarks. It is not intended for production use. diff --git a/examples/online_serving/cohere_rerank_client.py b/examples/online_serving/cohere_rerank_client.py index a07affe33..fc434ada1 100644 --- a/examples/online_serving/cohere_rerank_client.py +++ b/examples/online_serving/cohere_rerank_client.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """ Example of using the OpenAI entrypoint's rerank API which is compatible with the Cohere SDK: https://github.com/cohere-ai/cohere-python diff --git a/examples/online_serving/gradio_openai_chatbot_webserver.py b/examples/online_serving/gradio_openai_chatbot_webserver.py index 8ceb8f68e..ee01e1eae 100644 --- a/examples/online_serving/gradio_openai_chatbot_webserver.py +++ b/examples/online_serving/gradio_openai_chatbot_webserver.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import argparse import gradio as gr diff --git a/examples/online_serving/gradio_webserver.py b/examples/online_serving/gradio_webserver.py index 54e907582..c619146b0 100644 --- a/examples/online_serving/gradio_webserver.py +++ b/examples/online_serving/gradio_webserver.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import argparse import json diff --git a/examples/online_serving/jinaai_rerank_client.py b/examples/online_serving/jinaai_rerank_client.py index bf4de76dd..3e760e171 100644 --- a/examples/online_serving/jinaai_rerank_client.py +++ b/examples/online_serving/jinaai_rerank_client.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """ Example of using the OpenAI entrypoint's rerank API which is compatible with Jina and Cohere https://jina.ai/reranker diff --git a/examples/online_serving/openai_chat_completion_client.py b/examples/online_serving/openai_chat_completion_client.py index bbada3891..a81562041 100644 --- a/examples/online_serving/openai_chat_completion_client.py +++ b/examples/online_serving/openai_chat_completion_client.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from openai import OpenAI # Modify OpenAI's API key and API base to use vLLM's API server. diff --git a/examples/online_serving/openai_chat_completion_client_for_multimodal.py b/examples/online_serving/openai_chat_completion_client_for_multimodal.py index 03cc037bb..d5f798a8d 100644 --- a/examples/online_serving/openai_chat_completion_client_for_multimodal.py +++ b/examples/online_serving/openai_chat_completion_client_for_multimodal.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """An example showing how to use vLLM to serve multimodal models and run online serving with OpenAI client. diff --git a/examples/online_serving/openai_chat_completion_client_with_tools.py b/examples/online_serving/openai_chat_completion_client_with_tools.py index 2bbe42b6b..416fb61ca 100644 --- a/examples/online_serving/openai_chat_completion_client_with_tools.py +++ b/examples/online_serving/openai_chat_completion_client_with_tools.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """ Set up this example by starting a vLLM OpenAI-compatible server with tool call options enabled. For example: diff --git a/examples/online_serving/openai_chat_completion_structured_outputs.py b/examples/online_serving/openai_chat_completion_structured_outputs.py index 8c059c7ca..cddd93180 100644 --- a/examples/online_serving/openai_chat_completion_structured_outputs.py +++ b/examples/online_serving/openai_chat_completion_structured_outputs.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from enum import Enum from openai import OpenAI diff --git a/examples/online_serving/openai_chat_completion_with_reasoning.py b/examples/online_serving/openai_chat_completion_with_reasoning.py index 83e51a48b..a88c8adb5 100644 --- a/examples/online_serving/openai_chat_completion_with_reasoning.py +++ b/examples/online_serving/openai_chat_completion_with_reasoning.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """ An example shows how to generate chat completions from reasoning models like DeepSeekR1. diff --git a/examples/online_serving/openai_chat_completion_with_reasoning_streaming.py b/examples/online_serving/openai_chat_completion_with_reasoning_streaming.py index 8c14aac6b..489bfcd5e 100644 --- a/examples/online_serving/openai_chat_completion_with_reasoning_streaming.py +++ b/examples/online_serving/openai_chat_completion_with_reasoning_streaming.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """ An example shows how to generate chat completions from reasoning models like DeepSeekR1. diff --git a/examples/online_serving/openai_chat_embedding_client_for_multimodal.py b/examples/online_serving/openai_chat_embedding_client_for_multimodal.py index a56e7429b..f49d7a228 100644 --- a/examples/online_serving/openai_chat_embedding_client_for_multimodal.py +++ b/examples/online_serving/openai_chat_embedding_client_for_multimodal.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import argparse import base64 import io diff --git a/examples/online_serving/openai_completion_client.py b/examples/online_serving/openai_completion_client.py index 58519f978..06b93d7d1 100644 --- a/examples/online_serving/openai_completion_client.py +++ b/examples/online_serving/openai_completion_client.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from openai import OpenAI # Modify OpenAI's API key and API base to use vLLM's API server. diff --git a/examples/online_serving/openai_cross_encoder_score.py b/examples/online_serving/openai_cross_encoder_score.py index 365a684d5..67c5fc91b 100644 --- a/examples/online_serving/openai_cross_encoder_score.py +++ b/examples/online_serving/openai_cross_encoder_score.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """ Example online usage of Score API. diff --git a/examples/online_serving/openai_embedding_client.py b/examples/online_serving/openai_embedding_client.py index 4bd7ca01d..cb1109974 100644 --- a/examples/online_serving/openai_embedding_client.py +++ b/examples/online_serving/openai_embedding_client.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from openai import OpenAI # Modify OpenAI's API key and API base to use vLLM's API server. diff --git a/examples/online_serving/openai_pooling_client.py b/examples/online_serving/openai_pooling_client.py index 37ec8f2fb..e17f9c5ef 100644 --- a/examples/online_serving/openai_pooling_client.py +++ b/examples/online_serving/openai_pooling_client.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """ Example online usage of Pooling API. diff --git a/examples/online_serving/opentelemetry/dummy_client.py b/examples/online_serving/opentelemetry/dummy_client.py index b1a2b3c3c..7a605f85b 100644 --- a/examples/online_serving/opentelemetry/dummy_client.py +++ b/examples/online_serving/opentelemetry/dummy_client.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import requests from opentelemetry.exporter.otlp.proto.grpc.trace_exporter import ( OTLPSpanExporter) diff --git a/examples/other/tensorize_vllm_model.py b/examples/other/tensorize_vllm_model.py index 5fff1fdf5..68345e6cb 100644 --- a/examples/other/tensorize_vllm_model.py +++ b/examples/other/tensorize_vllm_model.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import argparse import dataclasses import json diff --git a/find_cuda_init.py b/find_cuda_init.py index 51db23102..0d13b2f86 100644 --- a/find_cuda_init.py +++ b/find_cuda_init.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import importlib import traceback from typing import Callable diff --git a/python_only_dev.py b/python_only_dev.py index 7d95ac96e..a303697b7 100644 --- a/python_only_dev.py +++ b/python_only_dev.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + msg = """Old style python only build (without compilation) is deprecated, please check https://docs.vllm.ai/en/latest/getting_started/installation.html#python-only-build-without-compilation for the new way to do python only build (without compilation). TL;DR: diff --git a/setup.py b/setup.py index 50a2392a4..50265d46e 100755 --- a/setup.py +++ b/setup.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import ctypes import importlib.util import logging diff --git a/tests/async_engine/api_server_async_engine.py b/tests/async_engine/api_server_async_engine.py index a3c9d5c6e..d9ac61164 100644 --- a/tests/async_engine/api_server_async_engine.py +++ b/tests/async_engine/api_server_async_engine.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """vllm.entrypoints.api_server with some extra logging for testing.""" from typing import Any, Dict, Iterable diff --git a/tests/async_engine/test_api_server.py b/tests/async_engine/test_api_server.py index 91ac35dd6..77f3fb002 100644 --- a/tests/async_engine/test_api_server.py +++ b/tests/async_engine/test_api_server.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import subprocess import sys import time diff --git a/tests/async_engine/test_async_llm_engine.py b/tests/async_engine/test_async_llm_engine.py index 8a04693ba..ca29abc92 100644 --- a/tests/async_engine/test_async_llm_engine.py +++ b/tests/async_engine/test_async_llm_engine.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import asyncio import os import uuid diff --git a/tests/async_engine/test_request_tracker.py b/tests/async_engine/test_request_tracker.py index 5668cc30d..fd6d89d4e 100644 --- a/tests/async_engine/test_request_tracker.py +++ b/tests/async_engine/test_request_tracker.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import pytest from vllm.engine.async_llm_engine import RequestTracker diff --git a/tests/basic_correctness/test_basic_correctness.py b/tests/basic_correctness/test_basic_correctness.py index 232850406..2792dfde7 100644 --- a/tests/basic_correctness/test_basic_correctness.py +++ b/tests/basic_correctness/test_basic_correctness.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Compare the short outputs of HF and vLLM when using greedy sampling. Run `pytest tests/basic_correctness/test_basic_correctness.py`. diff --git a/tests/basic_correctness/test_chunked_prefill.py b/tests/basic_correctness/test_chunked_prefill.py index 469d18a4d..cefd54d1c 100644 --- a/tests/basic_correctness/test_chunked_prefill.py +++ b/tests/basic_correctness/test_chunked_prefill.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Compare the outputs of HF and vLLM when using greedy sampling. It tests chunked prefill. Chunked prefill can be enabled by diff --git a/tests/basic_correctness/test_cpu_offload.py b/tests/basic_correctness/test_cpu_offload.py index d7f36a781..b4d558ce2 100644 --- a/tests/basic_correctness/test_cpu_offload.py +++ b/tests/basic_correctness/test_cpu_offload.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from ..utils import compare_two_settings diff --git a/tests/basic_correctness/test_cumem.py b/tests/basic_correctness/test_cumem.py index 53f4ef08f..da9239b09 100644 --- a/tests/basic_correctness/test_cumem.py +++ b/tests/basic_correctness/test_cumem.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import torch from vllm import LLM, SamplingParams diff --git a/tests/basic_correctness/test_preemption.py b/tests/basic_correctness/test_preemption.py index 4b27dcbc8..6aaec6eef 100644 --- a/tests/basic_correctness/test_preemption.py +++ b/tests/basic_correctness/test_preemption.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Compare the short outputs of HF and vLLM when using greedy sampling. VLLM_TEST_ENABLE_ARTIFICIAL_PREEMPT=1 has to be set before running this test. diff --git a/tests/compile/backend.py b/tests/compile/backend.py index 8fa10e5bd..74bc58a2d 100644 --- a/tests/compile/backend.py +++ b/tests/compile/backend.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from copy import deepcopy from typing import Callable, Union diff --git a/tests/compile/piecewise/test_simple.py b/tests/compile/piecewise/test_simple.py index aa1152481..9d633ad25 100644 --- a/tests/compile/piecewise/test_simple.py +++ b/tests/compile/piecewise/test_simple.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """ Test the piecewise compilation with a simple model so that we can exactly calculate the expected output and side effects. diff --git a/tests/compile/piecewise/test_toy_llama.py b/tests/compile/piecewise/test_toy_llama.py index d4ede4d23..0404722ba 100644 --- a/tests/compile/piecewise/test_toy_llama.py +++ b/tests/compile/piecewise/test_toy_llama.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """ Test the piecewise compilation with a simple model, comparing the output with and without the piecewise compilation. diff --git a/tests/compile/test_basic_correctness.py b/tests/compile/test_basic_correctness.py index 1945479fc..d7acec690 100644 --- a/tests/compile/test_basic_correctness.py +++ b/tests/compile/test_basic_correctness.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import dataclasses from typing import Dict, List, Optional diff --git a/tests/compile/test_full_graph.py b/tests/compile/test_full_graph.py index 4dfdfe21a..6e83fa368 100644 --- a/tests/compile/test_full_graph.py +++ b/tests/compile/test_full_graph.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import pytest from vllm.config import CompilationLevel diff --git a/tests/compile/test_functionalization.py b/tests/compile/test_functionalization.py index ea3aaee95..8f5040522 100644 --- a/tests/compile/test_functionalization.py +++ b/tests/compile/test_functionalization.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import pytest import torch diff --git a/tests/compile/test_fusion.py b/tests/compile/test_fusion.py index b4266a4a7..c14f0caab 100644 --- a/tests/compile/test_fusion.py +++ b/tests/compile/test_fusion.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import pytest import torch from compressed_tensors.quantization import FP8_DTYPE diff --git a/tests/compile/test_pass_manager.py b/tests/compile/test_pass_manager.py index 03e753509..70920ab10 100644 --- a/tests/compile/test_pass_manager.py +++ b/tests/compile/test_pass_manager.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import pickle import pytest diff --git a/tests/compile/test_wrapper.py b/tests/compile/test_wrapper.py index 74f66baaa..0934c6113 100644 --- a/tests/compile/test_wrapper.py +++ b/tests/compile/test_wrapper.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Optional import torch diff --git a/tests/compile/utils.py b/tests/compile/utils.py index 7c92d165d..e4a88584e 100644 --- a/tests/compile/utils.py +++ b/tests/compile/utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import os import torch diff --git a/tests/conftest.py b/tests/conftest.py index 279c1bf9a..85dd5bcb0 100644 --- a/tests/conftest.py +++ b/tests/conftest.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import json import os import tempfile diff --git a/tests/core/block/conftest.py b/tests/core/block/conftest.py index 0464d6a74..b7a9863f4 100644 --- a/tests/core/block/conftest.py +++ b/tests/core/block/conftest.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import pytest diff --git a/tests/core/block/e2e/conftest.py b/tests/core/block/e2e/conftest.py index 70577ec05..7d3ccaada 100644 --- a/tests/core/block/e2e/conftest.py +++ b/tests/core/block/e2e/conftest.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Callable, Iterable, Optional import pytest diff --git a/tests/core/block/e2e/test_correctness.py b/tests/core/block/e2e/test_correctness.py index 86502f613..e9b537ed5 100644 --- a/tests/core/block/e2e/test_correctness.py +++ b/tests/core/block/e2e/test_correctness.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from itertools import cycle import pytest diff --git a/tests/core/block/e2e/test_correctness_sliding_window.py b/tests/core/block/e2e/test_correctness_sliding_window.py index 415d0bd82..c874608e4 100644 --- a/tests/core/block/e2e/test_correctness_sliding_window.py +++ b/tests/core/block/e2e/test_correctness_sliding_window.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import random from typing import List diff --git a/tests/core/block/test_block_manager.py b/tests/core/block/test_block_manager.py index cfd749ad5..68d9618ae 100644 --- a/tests/core/block/test_block_manager.py +++ b/tests/core/block/test_block_manager.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import pytest from vllm.core.block.utils import (STR_NOT_IMPL_ENC_DEC_PREFIX_CACHE, diff --git a/tests/core/block/test_block_table.py b/tests/core/block/test_block_table.py index e2391a568..d8cf0bec7 100644 --- a/tests/core/block/test_block_table.py +++ b/tests/core/block/test_block_table.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List import pytest diff --git a/tests/core/block/test_common.py b/tests/core/block/test_common.py index cfdd3582e..202608730 100644 --- a/tests/core/block/test_common.py +++ b/tests/core/block/test_common.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import random import pytest diff --git a/tests/core/block/test_cpu_gpu_block_allocator.py b/tests/core/block/test_cpu_gpu_block_allocator.py index a9e38d404..a1414edd9 100644 --- a/tests/core/block/test_cpu_gpu_block_allocator.py +++ b/tests/core/block/test_cpu_gpu_block_allocator.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import pytest from vllm.core.block.cpu_gpu_block_allocator import CpuGpuBlockAllocator diff --git a/tests/core/block/test_naive_block.py b/tests/core/block/test_naive_block.py index 10d5964dc..0ca2a0b80 100644 --- a/tests/core/block/test_naive_block.py +++ b/tests/core/block/test_naive_block.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List, Optional import pytest diff --git a/tests/core/block/test_prefix_caching_block.py b/tests/core/block/test_prefix_caching_block.py index 6642174c1..771627a57 100644 --- a/tests/core/block/test_prefix_caching_block.py +++ b/tests/core/block/test_prefix_caching_block.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import math import random from typing import List, Optional diff --git a/tests/core/test_chunked_prefill_scheduler.py b/tests/core/test_chunked_prefill_scheduler.py index eaaf004df..8da25aea4 100644 --- a/tests/core/test_chunked_prefill_scheduler.py +++ b/tests/core/test_chunked_prefill_scheduler.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List from unittest.mock import MagicMock diff --git a/tests/core/test_num_computed_tokens_update.py b/tests/core/test_num_computed_tokens_update.py index bd4accab7..a4a901444 100644 --- a/tests/core/test_num_computed_tokens_update.py +++ b/tests/core/test_num_computed_tokens_update.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import pytest from tests.conftest import VllmRunner diff --git a/tests/core/test_scheduler.py b/tests/core/test_scheduler.py index 8f6de84e5..dcc97ebaa 100644 --- a/tests/core/test_scheduler.py +++ b/tests/core/test_scheduler.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import time from collections import deque from typing import List, Set, Tuple diff --git a/tests/core/test_scheduler_encoder_decoder.py b/tests/core/test_scheduler_encoder_decoder.py index 16bea5493..a4e3c73a5 100644 --- a/tests/core/test_scheduler_encoder_decoder.py +++ b/tests/core/test_scheduler_encoder_decoder.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List import pytest # noqa diff --git a/tests/core/test_serialization.py b/tests/core/test_serialization.py index d604e5250..64b3e148e 100644 --- a/tests/core/test_serialization.py +++ b/tests/core/test_serialization.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import msgspec from vllm.executor.msgspec_utils import decode_hook, encode_hook diff --git a/tests/core/utils.py b/tests/core/utils.py index 16703cd19..fb77dccce 100644 --- a/tests/core/utils.py +++ b/tests/core/utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import time from collections import defaultdict from typing import Any, Dict, List, Optional diff --git a/tests/distributed/test_ca_buffer_sharing.py b/tests/distributed/test_ca_buffer_sharing.py index fc4043cd3..72e7ebdb7 100644 --- a/tests/distributed/test_ca_buffer_sharing.py +++ b/tests/distributed/test_ca_buffer_sharing.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # can only run on machines with p2p access across GPUs # can only run with torchrun: # torchrun --nproc_per_node=2 tests/distributed/test_ca_buffer_sharing.py diff --git a/tests/distributed/test_comm_ops.py b/tests/distributed/test_comm_ops.py index d01f18752..bc916e8de 100644 --- a/tests/distributed/test_comm_ops.py +++ b/tests/distributed/test_comm_ops.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Test the communication operators. Run `pytest tests/distributed/test_comm_ops.py`. diff --git a/tests/distributed/test_custom_all_reduce.py b/tests/distributed/test_custom_all_reduce.py index 4072616fd..46887bca4 100644 --- a/tests/distributed/test_custom_all_reduce.py +++ b/tests/distributed/test_custom_all_reduce.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import os import random diff --git a/tests/distributed/test_distributed_oot.py b/tests/distributed/test_distributed_oot.py index 62e77a2f7..4b0c65d1d 100644 --- a/tests/distributed/test_distributed_oot.py +++ b/tests/distributed/test_distributed_oot.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from ..entrypoints.openai.test_oot_registration import ( run_and_test_dummy_opt_api_server) diff --git a/tests/distributed/test_multi_node_assignment.py b/tests/distributed/test_multi_node_assignment.py index 9f9c0ff07..c86d2d8a0 100644 --- a/tests/distributed/test_multi_node_assignment.py +++ b/tests/distributed/test_multi_node_assignment.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Make sure ray assigns GPU workers to the correct node. Run: diff --git a/tests/distributed/test_pipeline_parallel.py b/tests/distributed/test_pipeline_parallel.py index ddbf40f08..5b6741d74 100644 --- a/tests/distributed/test_pipeline_parallel.py +++ b/tests/distributed/test_pipeline_parallel.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """ WARNING: This test runs in both single-node (4 GPUs) and multi-node (2 node with 2 GPUs each) modes. If the test only uses 2 GPUs, it is diff --git a/tests/distributed/test_pipeline_partition.py b/tests/distributed/test_pipeline_partition.py index 2d4d07dd2..3ed104820 100644 --- a/tests/distributed/test_pipeline_partition.py +++ b/tests/distributed/test_pipeline_partition.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import os import pytest diff --git a/tests/distributed/test_pp_cudagraph.py b/tests/distributed/test_pp_cudagraph.py index 4912858d8..3bc85b05e 100644 --- a/tests/distributed/test_pp_cudagraph.py +++ b/tests/distributed/test_pp_cudagraph.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import os import pytest diff --git a/tests/distributed/test_pynccl.py b/tests/distributed/test_pynccl.py index a8571a115..4c42a0ed8 100644 --- a/tests/distributed/test_pynccl.py +++ b/tests/distributed/test_pynccl.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import multiprocessing import os from typing import Dict, List diff --git a/tests/distributed/test_same_node.py b/tests/distributed/test_same_node.py index 62311a626..9b1bbd6e5 100644 --- a/tests/distributed/test_same_node.py +++ b/tests/distributed/test_same_node.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import os import torch.distributed as dist diff --git a/tests/distributed/test_shm_broadcast.py b/tests/distributed/test_shm_broadcast.py index 723872682..59fa7cc9f 100644 --- a/tests/distributed/test_shm_broadcast.py +++ b/tests/distributed/test_shm_broadcast.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import multiprocessing import random import time diff --git a/tests/distributed/test_torchrun_example.py b/tests/distributed/test_torchrun_example.py index 7aa03d7f0..a092a548a 100644 --- a/tests/distributed/test_torchrun_example.py +++ b/tests/distributed/test_torchrun_example.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # unit test for `examples/offline_inference/torchrun_example.py` import random diff --git a/tests/distributed/test_utils.py b/tests/distributed/test_utils.py index 5fb1ae7b2..4432950f2 100644 --- a/tests/distributed/test_utils.py +++ b/tests/distributed/test_utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import socket import pytest diff --git a/tests/encoder_decoder/test_e2e_correctness.py b/tests/encoder_decoder/test_e2e_correctness.py index fa5d6a69a..d0e4f8625 100644 --- a/tests/encoder_decoder/test_e2e_correctness.py +++ b/tests/encoder_decoder/test_e2e_correctness.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """E2E tests to verify the correctness of the encoder-decoder framework Run `pytest tests/encoder_decoder/test_e2e_correctness.py`. diff --git a/tests/engine/output_processor/test_multi_step.py b/tests/engine/output_processor/test_multi_step.py index 88f3fad4c..3ba3c4ec5 100644 --- a/tests/engine/output_processor/test_multi_step.py +++ b/tests/engine/output_processor/test_multi_step.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import random from unittest.mock import MagicMock diff --git a/tests/engine/output_processor/test_stop_checker.py b/tests/engine/output_processor/test_stop_checker.py index cc14e8cbf..e9ad8d161 100644 --- a/tests/engine/output_processor/test_stop_checker.py +++ b/tests/engine/output_processor/test_stop_checker.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from unittest.mock import MagicMock import pytest diff --git a/tests/engine/test_arg_utils.py b/tests/engine/test_arg_utils.py index 4e269de9f..8698d124e 100644 --- a/tests/engine/test_arg_utils.py +++ b/tests/engine/test_arg_utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from argparse import ArgumentTypeError import pytest diff --git a/tests/engine/test_computed_prefix_blocks.py b/tests/engine/test_computed_prefix_blocks.py index ed35212cc..dca8fa602 100644 --- a/tests/engine/test_computed_prefix_blocks.py +++ b/tests/engine/test_computed_prefix_blocks.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import pytest from vllm.engine.arg_utils import EngineArgs diff --git a/tests/engine/test_custom_executor.py b/tests/engine/test_custom_executor.py index 0e33f3662..3e77faecb 100644 --- a/tests/engine/test_custom_executor.py +++ b/tests/engine/test_custom_executor.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import asyncio import os from typing import Any, Callable, Dict, List, Optional, Tuple, Union diff --git a/tests/engine/test_detokenization.py b/tests/engine/test_detokenization.py index f77f6d072..742176ea8 100644 --- a/tests/engine/test_detokenization.py +++ b/tests/engine/test_detokenization.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import pytest from vllm.entrypoints.llm import LLM diff --git a/tests/engine/test_multiproc_workers.py b/tests/engine/test_multiproc_workers.py index 04505fcaa..f1fe58e35 100644 --- a/tests/engine/test_multiproc_workers.py +++ b/tests/engine/test_multiproc_workers.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import asyncio from concurrent.futures import ThreadPoolExecutor from functools import partial diff --git a/tests/engine/test_short_mm_context.py b/tests/engine/test_short_mm_context.py index a6ba7a131..d5111e3fd 100644 --- a/tests/engine/test_short_mm_context.py +++ b/tests/engine/test_short_mm_context.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import pytest from ..conftest import IMAGE_ASSETS diff --git a/tests/engine/test_skip_tokenizer_init.py b/tests/engine/test_skip_tokenizer_init.py index b8818af56..655c8232a 100644 --- a/tests/engine/test_skip_tokenizer_init.py +++ b/tests/engine/test_skip_tokenizer_init.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import pytest from vllm.entrypoints.llm import LLM diff --git a/tests/engine/test_stop_reason.py b/tests/engine/test_stop_reason.py index b0bd6c4aa..a50b38804 100644 --- a/tests/engine/test_stop_reason.py +++ b/tests/engine/test_stop_reason.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Test the different finish_reason="stop" situations during generation: 1. One of the provided stop strings 2. One of the provided stop tokens diff --git a/tests/engine/test_stop_strings.py b/tests/engine/test_stop_strings.py index 499935620..0f633bb26 100644 --- a/tests/engine/test_stop_strings.py +++ b/tests/engine/test_stop_strings.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Any, List, Optional import pytest diff --git a/tests/entrypoints/conftest.py b/tests/entrypoints/conftest.py index ef74062ce..b00e168db 100644 --- a/tests/entrypoints/conftest.py +++ b/tests/entrypoints/conftest.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import pytest diff --git a/tests/entrypoints/llm/test_accuracy.py b/tests/entrypoints/llm/test_accuracy.py index 6bf7190a6..29ff00df6 100644 --- a/tests/entrypoints/llm/test_accuracy.py +++ b/tests/entrypoints/llm/test_accuracy.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """ This file test accuracy of the vLLM server via LMEval. It uses local-completions, which interacts with vLLM diff --git a/tests/entrypoints/llm/test_chat.py b/tests/entrypoints/llm/test_chat.py index fc66386fd..77c80b2f8 100644 --- a/tests/entrypoints/llm/test_chat.py +++ b/tests/entrypoints/llm/test_chat.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List import pytest diff --git a/tests/entrypoints/llm/test_collective_rpc.py b/tests/entrypoints/llm/test_collective_rpc.py index 22473ce27..39d4810de 100644 --- a/tests/entrypoints/llm/test_collective_rpc.py +++ b/tests/entrypoints/llm/test_collective_rpc.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import pytest from vllm import LLM diff --git a/tests/entrypoints/llm/test_encode.py b/tests/entrypoints/llm/test_encode.py index 3906ad766..ebec8baba 100644 --- a/tests/entrypoints/llm/test_encode.py +++ b/tests/entrypoints/llm/test_encode.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import weakref from typing import List diff --git a/tests/entrypoints/llm/test_generate.py b/tests/entrypoints/llm/test_generate.py index 7d2b37775..4c78c2c8e 100644 --- a/tests/entrypoints/llm/test_generate.py +++ b/tests/entrypoints/llm/test_generate.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import weakref from typing import List diff --git a/tests/entrypoints/llm/test_generate_multiple_loras.py b/tests/entrypoints/llm/test_generate_multiple_loras.py index eb2113692..90e1d5814 100644 --- a/tests/entrypoints/llm/test_generate_multiple_loras.py +++ b/tests/entrypoints/llm/test_generate_multiple_loras.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import weakref import pytest diff --git a/tests/entrypoints/llm/test_gpu_utilization.py b/tests/entrypoints/llm/test_gpu_utilization.py index c2dab300e..c2b4a9358 100644 --- a/tests/entrypoints/llm/test_gpu_utilization.py +++ b/tests/entrypoints/llm/test_gpu_utilization.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from vllm import LLM, SamplingParams diff --git a/tests/entrypoints/llm/test_guided_generate.py b/tests/entrypoints/llm/test_guided_generate.py index ccb9906fc..932a35a99 100644 --- a/tests/entrypoints/llm/test_guided_generate.py +++ b/tests/entrypoints/llm/test_guided_generate.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import json import re import weakref diff --git a/tests/entrypoints/llm/test_init.py b/tests/entrypoints/llm/test_init.py index c9a4ad44f..925bf56a9 100644 --- a/tests/entrypoints/llm/test_init.py +++ b/tests/entrypoints/llm/test_init.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import pytest from vllm import LLM diff --git a/tests/entrypoints/llm/test_lazy_outlines.py b/tests/entrypoints/llm/test_lazy_outlines.py index bf609b38a..b1f9ae14d 100644 --- a/tests/entrypoints/llm/test_lazy_outlines.py +++ b/tests/entrypoints/llm/test_lazy_outlines.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import sys from contextlib import nullcontext diff --git a/tests/entrypoints/llm/test_prompt_validation.py b/tests/entrypoints/llm/test_prompt_validation.py index ee7010a23..f2c145fa3 100644 --- a/tests/entrypoints/llm/test_prompt_validation.py +++ b/tests/entrypoints/llm/test_prompt_validation.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import pytest from vllm import LLM diff --git a/tests/entrypoints/offline_mode/test_offline_mode.py b/tests/entrypoints/offline_mode/test_offline_mode.py index 65699e609..eac76f2ba 100644 --- a/tests/entrypoints/offline_mode/test_offline_mode.py +++ b/tests/entrypoints/offline_mode/test_offline_mode.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Tests for HF_HUB_OFFLINE mode""" import importlib import sys diff --git a/tests/entrypoints/openai/reasoning_parsers/test_deepseekr1_reasoning_parser.py b/tests/entrypoints/openai/reasoning_parsers/test_deepseekr1_reasoning_parser.py index 4607e4dfe..f7b81be48 100644 --- a/tests/entrypoints/openai/reasoning_parsers/test_deepseekr1_reasoning_parser.py +++ b/tests/entrypoints/openai/reasoning_parsers/test_deepseekr1_reasoning_parser.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List import pytest diff --git a/tests/entrypoints/openai/reasoning_parsers/utils.py b/tests/entrypoints/openai/reasoning_parsers/utils.py index ac73ad50a..2157e0595 100644 --- a/tests/entrypoints/openai/reasoning_parsers/utils.py +++ b/tests/entrypoints/openai/reasoning_parsers/utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List, Optional, Tuple, Union from vllm.entrypoints.openai.protocol import (ChatCompletionRequest, diff --git a/tests/entrypoints/openai/test_accuracy.py b/tests/entrypoints/openai/test_accuracy.py index b1d4461d1..df25780cd 100644 --- a/tests/entrypoints/openai/test_accuracy.py +++ b/tests/entrypoints/openai/test_accuracy.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """ This file test accuracy of the vLLM server via LMEval. It uses local-completions, which interacts with vLLM diff --git a/tests/entrypoints/openai/test_async_tokenization.py b/tests/entrypoints/openai/test_async_tokenization.py index fcce8b46c..1f7ba0da4 100644 --- a/tests/entrypoints/openai/test_async_tokenization.py +++ b/tests/entrypoints/openai/test_async_tokenization.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import asyncio import contextlib import random diff --git a/tests/entrypoints/openai/test_audio.py b/tests/entrypoints/openai/test_audio.py index 1116c0da1..6e206dfd9 100644 --- a/tests/entrypoints/openai/test_audio.py +++ b/tests/entrypoints/openai/test_audio.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Dict, List import openai diff --git a/tests/entrypoints/openai/test_basic.py b/tests/entrypoints/openai/test_basic.py index 547c1fd02..0d44a7611 100644 --- a/tests/entrypoints/openai/test_basic.py +++ b/tests/entrypoints/openai/test_basic.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import asyncio from http import HTTPStatus from typing import List diff --git a/tests/entrypoints/openai/test_chat.py b/tests/entrypoints/openai/test_chat.py index 5e6499d8f..4b5ad55c5 100644 --- a/tests/entrypoints/openai/test_chat.py +++ b/tests/entrypoints/openai/test_chat.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # imports for guided decoding tests import json import re diff --git a/tests/entrypoints/openai/test_chat_echo.py b/tests/entrypoints/openai/test_chat_echo.py index 223ac5b41..3e76158a8 100644 --- a/tests/entrypoints/openai/test_chat_echo.py +++ b/tests/entrypoints/openai/test_chat_echo.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import NamedTuple import openai # use the official client for correctness check diff --git a/tests/entrypoints/openai/test_chat_template.py b/tests/entrypoints/openai/test_chat_template.py index e1e1dcff7..255aba139 100644 --- a/tests/entrypoints/openai/test_chat_template.py +++ b/tests/entrypoints/openai/test_chat_template.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import pytest from vllm.entrypoints.chat_utils import (apply_hf_chat_template, diff --git a/tests/entrypoints/openai/test_chunked_prompt.py b/tests/entrypoints/openai/test_chunked_prompt.py index 61d663651..0419395f1 100644 --- a/tests/entrypoints/openai/test_chunked_prompt.py +++ b/tests/entrypoints/openai/test_chunked_prompt.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import openai # use the official client for correctness check import pytest import pytest_asyncio diff --git a/tests/entrypoints/openai/test_cli_args.py b/tests/entrypoints/openai/test_cli_args.py index 01bcd78aa..2f065ec10 100644 --- a/tests/entrypoints/openai/test_cli_args.py +++ b/tests/entrypoints/openai/test_cli_args.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import json import pytest diff --git a/tests/entrypoints/openai/test_completion.py b/tests/entrypoints/openai/test_completion.py index 183d900c4..28671cc27 100644 --- a/tests/entrypoints/openai/test_completion.py +++ b/tests/entrypoints/openai/test_completion.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # imports for guided decoding tests import json import re diff --git a/tests/entrypoints/openai/test_embedding.py b/tests/entrypoints/openai/test_embedding.py index b52a5b28c..e86ea87dd 100644 --- a/tests/entrypoints/openai/test_embedding.py +++ b/tests/entrypoints/openai/test_embedding.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import base64 import numpy as np diff --git a/tests/entrypoints/openai/test_encoder_decoder.py b/tests/entrypoints/openai/test_encoder_decoder.py index 51eba694e..52b4df9ce 100644 --- a/tests/entrypoints/openai/test_encoder_decoder.py +++ b/tests/entrypoints/openai/test_encoder_decoder.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import openai import pytest import pytest_asyncio diff --git a/tests/entrypoints/openai/test_lora_adapters.py b/tests/entrypoints/openai/test_lora_adapters.py index 6ff99f6fa..1a62157ac 100644 --- a/tests/entrypoints/openai/test_lora_adapters.py +++ b/tests/entrypoints/openai/test_lora_adapters.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import asyncio import json import shutil diff --git a/tests/entrypoints/openai/test_metrics.py b/tests/entrypoints/openai/test_metrics.py index 941f46571..a9134be62 100644 --- a/tests/entrypoints/openai/test_metrics.py +++ b/tests/entrypoints/openai/test_metrics.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import subprocess import sys import tempfile diff --git a/tests/entrypoints/openai/test_models.py b/tests/entrypoints/openai/test_models.py index ae5bf404d..3d4f1cde2 100644 --- a/tests/entrypoints/openai/test_models.py +++ b/tests/entrypoints/openai/test_models.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import openai # use the official client for correctness check import pytest import pytest_asyncio diff --git a/tests/entrypoints/openai/test_oot_registration.py b/tests/entrypoints/openai/test_oot_registration.py index b25cb1d0e..a1b7a205a 100644 --- a/tests/entrypoints/openai/test_oot_registration.py +++ b/tests/entrypoints/openai/test_oot_registration.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from ...utils import VLLM_PATH, RemoteOpenAIServer chatml_jinja_path = VLLM_PATH / "examples/template_chatml.jinja" diff --git a/tests/entrypoints/openai/test_pooling.py b/tests/entrypoints/openai/test_pooling.py index 9c4923939..11d3bfafa 100644 --- a/tests/entrypoints/openai/test_pooling.py +++ b/tests/entrypoints/openai/test_pooling.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import base64 import numpy as np diff --git a/tests/entrypoints/openai/test_prompt_validation.py b/tests/entrypoints/openai/test_prompt_validation.py index 1ae64ef49..64a1eb6a6 100644 --- a/tests/entrypoints/openai/test_prompt_validation.py +++ b/tests/entrypoints/openai/test_prompt_validation.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # imports for guided decoding tests import re diff --git a/tests/entrypoints/openai/test_rerank.py b/tests/entrypoints/openai/test_rerank.py index cfd8f3313..4c9774a73 100644 --- a/tests/entrypoints/openai/test_rerank.py +++ b/tests/entrypoints/openai/test_rerank.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import pytest import requests diff --git a/tests/entrypoints/openai/test_return_tokens_as_ids.py b/tests/entrypoints/openai/test_return_tokens_as_ids.py index 99f6da160..9b33eddae 100644 --- a/tests/entrypoints/openai/test_return_tokens_as_ids.py +++ b/tests/entrypoints/openai/test_return_tokens_as_ids.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Separate these tests out from test_completion and test_chat, because they # require launching a second server with a different flag. Running both servers # at the same time on a single node will OOM. diff --git a/tests/entrypoints/openai/test_root_path.py b/tests/entrypoints/openai/test_root_path.py index 20f796061..ad8159afc 100644 --- a/tests/entrypoints/openai/test_root_path.py +++ b/tests/entrypoints/openai/test_root_path.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import contextlib import os from typing import Any, List, NamedTuple diff --git a/tests/entrypoints/openai/test_run_batch.py b/tests/entrypoints/openai/test_run_batch.py index 1f8a56bb4..db049ee2b 100644 --- a/tests/entrypoints/openai/test_run_batch.py +++ b/tests/entrypoints/openai/test_run_batch.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import json import subprocess import sys diff --git a/tests/entrypoints/openai/test_score.py b/tests/entrypoints/openai/test_score.py index 0d19615bc..bcbcb5702 100644 --- a/tests/entrypoints/openai/test_score.py +++ b/tests/entrypoints/openai/test_score.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import pytest import requests diff --git a/tests/entrypoints/openai/test_serving_chat.py b/tests/entrypoints/openai/test_serving_chat.py index e88d6c3c6..1e7dbaf60 100644 --- a/tests/entrypoints/openai/test_serving_chat.py +++ b/tests/entrypoints/openai/test_serving_chat.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import asyncio from contextlib import suppress from dataclasses import dataclass diff --git a/tests/entrypoints/openai/test_serving_models.py b/tests/entrypoints/openai/test_serving_models.py index 657ea2021..70ca8507a 100644 --- a/tests/entrypoints/openai/test_serving_models.py +++ b/tests/entrypoints/openai/test_serving_models.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from http import HTTPStatus from unittest.mock import MagicMock diff --git a/tests/entrypoints/openai/test_shutdown.py b/tests/entrypoints/openai/test_shutdown.py index 090523a83..5edf85ab5 100644 --- a/tests/entrypoints/openai/test_shutdown.py +++ b/tests/entrypoints/openai/test_shutdown.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import openai import pytest diff --git a/tests/entrypoints/openai/test_tokenization.py b/tests/entrypoints/openai/test_tokenization.py index b1956a8cb..663b72242 100644 --- a/tests/entrypoints/openai/test_tokenization.py +++ b/tests/entrypoints/openai/test_tokenization.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import pytest import pytest_asyncio import requests diff --git a/tests/entrypoints/openai/test_video.py b/tests/entrypoints/openai/test_video.py index e73449e40..ab9285407 100644 --- a/tests/entrypoints/openai/test_video.py +++ b/tests/entrypoints/openai/test_video.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Dict, List import openai diff --git a/tests/entrypoints/openai/test_vision.py b/tests/entrypoints/openai/test_vision.py index 5f070ba3b..029c9b038 100644 --- a/tests/entrypoints/openai/test_vision.py +++ b/tests/entrypoints/openai/test_vision.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Dict, List import openai diff --git a/tests/entrypoints/openai/test_vision_embedding.py b/tests/entrypoints/openai/test_vision_embedding.py index c851539c6..f2ff4a0b0 100644 --- a/tests/entrypoints/openai/test_vision_embedding.py +++ b/tests/entrypoints/openai/test_vision_embedding.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Dict import pytest diff --git a/tests/entrypoints/openai/tool_parsers/test_pythonic_tool_parser.py b/tests/entrypoints/openai/tool_parsers/test_pythonic_tool_parser.py index 47b0b6bb8..788efa86b 100644 --- a/tests/entrypoints/openai/tool_parsers/test_pythonic_tool_parser.py +++ b/tests/entrypoints/openai/tool_parsers/test_pythonic_tool_parser.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List from unittest.mock import MagicMock diff --git a/tests/entrypoints/openai/tool_parsers/utils.py b/tests/entrypoints/openai/tool_parsers/utils.py index f0a2a32c1..57ec98653 100644 --- a/tests/entrypoints/openai/tool_parsers/utils.py +++ b/tests/entrypoints/openai/tool_parsers/utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Iterable, List, Tuple, Union from vllm.entrypoints.openai.protocol import (ChatCompletionRequest, diff --git a/tests/entrypoints/test_chat_utils.py b/tests/entrypoints/test_chat_utils.py index 513b466c1..737f73309 100644 --- a/tests/entrypoints/test_chat_utils.py +++ b/tests/entrypoints/test_chat_utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import warnings from typing import Optional diff --git a/tests/kernels/allclose_default.py b/tests/kernels/allclose_default.py index 175cfe82f..97ceffab4 100644 --- a/tests/kernels/allclose_default.py +++ b/tests/kernels/allclose_default.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import torch # Reference default values of atol and rtol are from diff --git a/tests/kernels/conftest.py b/tests/kernels/conftest.py index 4f2f9cc3d..4f04ec947 100644 --- a/tests/kernels/conftest.py +++ b/tests/kernels/conftest.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import pytest from vllm.utils import (create_kv_caches_with_random, diff --git a/tests/kernels/quant_utils.py b/tests/kernels/quant_utils.py index f2358940f..34dcf91c7 100644 --- a/tests/kernels/quant_utils.py +++ b/tests/kernels/quant_utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Optional, Tuple, Union import torch diff --git a/tests/kernels/test_activation.py b/tests/kernels/test_activation.py index dac26efe8..2e70b1db3 100644 --- a/tests/kernels/test_activation.py +++ b/tests/kernels/test_activation.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import random from typing import Type diff --git a/tests/kernels/test_aqlm.py b/tests/kernels/test_aqlm.py index 860fb66b1..7d3617281 100644 --- a/tests/kernels/test_aqlm.py +++ b/tests/kernels/test_aqlm.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import torch from tests.kernels.utils import opcheck diff --git a/tests/kernels/test_attention.py b/tests/kernels/test_attention.py index 574a0f223..b667d8d9e 100644 --- a/tests/kernels/test_attention.py +++ b/tests/kernels/test_attention.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import random from typing import List, Optional, Tuple diff --git a/tests/kernels/test_attention_selector.py b/tests/kernels/test_attention_selector.py index 492acb91e..0e8743731 100644 --- a/tests/kernels/test_attention_selector.py +++ b/tests/kernels/test_attention_selector.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from unittest.mock import Mock, patch import pytest diff --git a/tests/kernels/test_awq.py b/tests/kernels/test_awq.py index aa7a43085..ace75a336 100644 --- a/tests/kernels/test_awq.py +++ b/tests/kernels/test_awq.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import os import pytest diff --git a/tests/kernels/test_awq_marlin.py b/tests/kernels/test_awq_marlin.py index 238d6426b..67595010c 100644 --- a/tests/kernels/test_awq_marlin.py +++ b/tests/kernels/test_awq_marlin.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Test AWQ with fused MoE Marlin kernels. Run `pytest tests/kernels/test_awq_marlin.py`. diff --git a/tests/kernels/test_awq_triton.py b/tests/kernels/test_awq_triton.py index 406a0c8dd..3fc3feaf4 100644 --- a/tests/kernels/test_awq_triton.py +++ b/tests/kernels/test_awq_triton.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Tests for the AWQ Triton kernel. Run `pytest tests/kernels/test_awq_triton.py`. diff --git a/tests/kernels/test_block_fp8.py b/tests/kernels/test_block_fp8.py index f28fdf3fe..20eff1c20 100644 --- a/tests/kernels/test_block_fp8.py +++ b/tests/kernels/test_block_fp8.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Adapted from https://github.com/sgl-project/sglang/pull/2575 import itertools diff --git a/tests/kernels/test_blocksparse_attention.py b/tests/kernels/test_blocksparse_attention.py index 08f31219e..e653d34d0 100644 --- a/tests/kernels/test_blocksparse_attention.py +++ b/tests/kernels/test_blocksparse_attention.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import random from typing import List, Optional, Tuple diff --git a/tests/kernels/test_cache.py b/tests/kernels/test_cache.py index c848be4f9..6f909b680 100644 --- a/tests/kernels/test_cache.py +++ b/tests/kernels/test_cache.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import random from typing import List, Tuple diff --git a/tests/kernels/test_cascade_flash_attn.py b/tests/kernels/test_cascade_flash_attn.py index 8edfde42e..8cc1a6a1b 100755 --- a/tests/kernels/test_cascade_flash_attn.py +++ b/tests/kernels/test_cascade_flash_attn.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List, Optional, Tuple import pytest diff --git a/tests/kernels/test_causal_conv1d.py b/tests/kernels/test_causal_conv1d.py index 51be2425d..93064e23d 100644 --- a/tests/kernels/test_causal_conv1d.py +++ b/tests/kernels/test_causal_conv1d.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Optional import pytest diff --git a/tests/kernels/test_cutlass.py b/tests/kernels/test_cutlass.py index f538d492c..49fd8ed63 100644 --- a/tests/kernels/test_cutlass.py +++ b/tests/kernels/test_cutlass.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Tests for cutlass kernels Run `pytest tests/kernels/test_cutlass.py`. diff --git a/tests/kernels/test_cutlass_2of4_sparse.py b/tests/kernels/test_cutlass_2of4_sparse.py index 56495df34..4c613b75f 100644 --- a/tests/kernels/test_cutlass_2of4_sparse.py +++ b/tests/kernels/test_cutlass_2of4_sparse.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Tests for sparse cutlass kernels Run `pytest tests/kernels/test_semi_structured.py`. diff --git a/tests/kernels/test_encoder_decoder_attn.py b/tests/kernels/test_encoder_decoder_attn.py index e008a56de..0d11e8652 100644 --- a/tests/kernels/test_encoder_decoder_attn.py +++ b/tests/kernels/test_encoder_decoder_attn.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """ Tests: diff --git a/tests/kernels/test_flash_attn.py b/tests/kernels/test_flash_attn.py index 0ee0bf6c6..b8af89b66 100644 --- a/tests/kernels/test_flash_attn.py +++ b/tests/kernels/test_flash_attn.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List, Optional, Tuple import pytest diff --git a/tests/kernels/test_flashinfer.py b/tests/kernels/test_flashinfer.py index 1645ef911..212ceb5e4 100644 --- a/tests/kernels/test_flashinfer.py +++ b/tests/kernels/test_flashinfer.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List, Optional, Tuple import flashinfer diff --git a/tests/kernels/test_fp8_quant.py b/tests/kernels/test_fp8_quant.py index ebaaae232..876cf03fd 100644 --- a/tests/kernels/test_fp8_quant.py +++ b/tests/kernels/test_fp8_quant.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import pytest import torch diff --git a/tests/kernels/test_fused_quant_layernorm.py b/tests/kernels/test_fused_quant_layernorm.py index baf8d73fd..d4b674b23 100644 --- a/tests/kernels/test_fused_quant_layernorm.py +++ b/tests/kernels/test_fused_quant_layernorm.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Optional, Tuple, Union import pytest diff --git a/tests/kernels/test_ggml.py b/tests/kernels/test_ggml.py index dddb285bf..dc728fd48 100644 --- a/tests/kernels/test_ggml.py +++ b/tests/kernels/test_ggml.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import gguf import pytest import torch diff --git a/tests/kernels/test_gguf.py b/tests/kernels/test_gguf.py index 893af99ba..847ca9f43 100644 --- a/tests/kernels/test_gguf.py +++ b/tests/kernels/test_gguf.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from pathlib import Path from typing import List diff --git a/tests/kernels/test_gptq.py b/tests/kernels/test_gptq.py index c1ca6f1f5..fea013d9e 100644 --- a/tests/kernels/test_gptq.py +++ b/tests/kernels/test_gptq.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import torch from tests.kernels.utils import opcheck diff --git a/tests/kernels/test_int8_quant.py b/tests/kernels/test_int8_quant.py index 761eb95c4..25dcb587e 100644 --- a/tests/kernels/test_int8_quant.py +++ b/tests/kernels/test_int8_quant.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import pytest import torch diff --git a/tests/kernels/test_layernorm.py b/tests/kernels/test_layernorm.py index 727769e07..fa4bbe458 100644 --- a/tests/kernels/test_layernorm.py +++ b/tests/kernels/test_layernorm.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import pytest import torch diff --git a/tests/kernels/test_machete_mm.py b/tests/kernels/test_machete_mm.py index 1c6eb2dd9..bd60526ed 100644 --- a/tests/kernels/test_machete_mm.py +++ b/tests/kernels/test_machete_mm.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Tests for the machete kernel. Run `pytest tests/kernels/test_machete_mm.py`. diff --git a/tests/kernels/test_mamba_ssm.py b/tests/kernels/test_mamba_ssm.py index 19d1158c7..84d4c347e 100644 --- a/tests/kernels/test_mamba_ssm.py +++ b/tests/kernels/test_mamba_ssm.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import pytest import torch import torch.nn.functional as F diff --git a/tests/kernels/test_marlin_gemm.py b/tests/kernels/test_marlin_gemm.py index 5e047f4b0..b96aca06c 100644 --- a/tests/kernels/test_marlin_gemm.py +++ b/tests/kernels/test_marlin_gemm.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Tests for the marlin kernel. Run `pytest tests/kernels/marlin/test_marlin_gemm.py`. diff --git a/tests/kernels/test_mha_attn.py b/tests/kernels/test_mha_attn.py index eab874e9e..5a18b7916 100644 --- a/tests/kernels/test_mha_attn.py +++ b/tests/kernels/test_mha_attn.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """ Test: diff --git a/tests/kernels/test_moe.py b/tests/kernels/test_moe.py index 7aa248ed1..0f13fbc96 100644 --- a/tests/kernels/test_moe.py +++ b/tests/kernels/test_moe.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Tests for the MOE layers. Run `pytest tests/kernels/test_moe.py`. diff --git a/tests/kernels/test_permute_cols.py b/tests/kernels/test_permute_cols.py index 14ad7a22c..35d62079f 100644 --- a/tests/kernels/test_permute_cols.py +++ b/tests/kernels/test_permute_cols.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import pytest import torch diff --git a/tests/kernels/test_pos_encoding.py b/tests/kernels/test_pos_encoding.py index eee77c22a..5b7b0fda2 100644 --- a/tests/kernels/test_pos_encoding.py +++ b/tests/kernels/test_pos_encoding.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from itertools import accumulate, product from typing import Dict, List, Optional diff --git a/tests/kernels/test_prefix_prefill.py b/tests/kernels/test_prefix_prefill.py index 10e73ab95..2184c9852 100644 --- a/tests/kernels/test_prefix_prefill.py +++ b/tests/kernels/test_prefix_prefill.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import math import random import time diff --git a/tests/kernels/test_rotary_embedding.py b/tests/kernels/test_rotary_embedding.py index da879406b..362bcb35c 100644 --- a/tests/kernels/test_rotary_embedding.py +++ b/tests/kernels/test_rotary_embedding.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """ Tests for miscellaneous utilities """ diff --git a/tests/kernels/test_triton_decode_attention.py b/tests/kernels/test_triton_decode_attention.py index 14f5a3b77..fd3c9fa41 100644 --- a/tests/kernels/test_triton_decode_attention.py +++ b/tests/kernels/test_triton_decode_attention.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import pytest import torch diff --git a/tests/kernels/test_triton_scaled_mm.py b/tests/kernels/test_triton_scaled_mm.py index a5aab3c2e..d878ed6f4 100644 --- a/tests/kernels/test_triton_scaled_mm.py +++ b/tests/kernels/test_triton_scaled_mm.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Tests for the triton_scaled_mm kernel Run `pytest tests/kernels/test_triton_scaled_mm.py`. diff --git a/tests/kernels/test_utils.py b/tests/kernels/test_utils.py index 7e5126a76..d3f032002 100644 --- a/tests/kernels/test_utils.py +++ b/tests/kernels/test_utils.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """ Tests for miscellaneous utilities """ diff --git a/tests/kernels/utils.py b/tests/kernels/utils.py index c735c5edd..5be111d71 100644 --- a/tests/kernels/utils.py +++ b/tests/kernels/utils.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Kernel test utils""" import itertools diff --git a/tests/kv_transfer/disagg_test.py b/tests/kv_transfer/disagg_test.py index adc6150ed..97e0d6eb1 100644 --- a/tests/kv_transfer/disagg_test.py +++ b/tests/kv_transfer/disagg_test.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import os import subprocess import sys diff --git a/tests/kv_transfer/module_test.py b/tests/kv_transfer/module_test.py index 355461919..8a6490b5c 100644 --- a/tests/kv_transfer/module_test.py +++ b/tests/kv_transfer/module_test.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import subprocess import sys diff --git a/tests/kv_transfer/test_lookup_buffer.py b/tests/kv_transfer/test_lookup_buffer.py index 4d6890305..c5b34660d 100644 --- a/tests/kv_transfer/test_lookup_buffer.py +++ b/tests/kv_transfer/test_lookup_buffer.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import os import random diff --git a/tests/kv_transfer/test_send_recv.py b/tests/kv_transfer/test_send_recv.py index 1cc1ced99..181a5ac20 100644 --- a/tests/kv_transfer/test_send_recv.py +++ b/tests/kv_transfer/test_send_recv.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import os import time from typing import List diff --git a/tests/lora/conftest.py b/tests/lora/conftest.py index e7378d007..071cdbecc 100644 --- a/tests/lora/conftest.py +++ b/tests/lora/conftest.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import tempfile from collections import OrderedDict from typing import Dict, List, TypedDict diff --git a/tests/lora/data/long_context_test_data.py b/tests/lora/data/long_context_test_data.py index 61b8899f0..2d33f738b 100644 --- a/tests/lora/data/long_context_test_data.py +++ b/tests/lora/data/long_context_test_data.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # ruff: noqa """This file contains a dictionary of prompts and golden responses.""" diff --git a/tests/lora/test_baichuan.py b/tests/lora/test_baichuan.py index 0ba2ce361..249f7619d 100644 --- a/tests/lora/test_baichuan.py +++ b/tests/lora/test_baichuan.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List import pytest diff --git a/tests/lora/test_chatglm3_tp.py b/tests/lora/test_chatglm3_tp.py index 49a527b99..0aa9fe7a9 100644 --- a/tests/lora/test_chatglm3_tp.py +++ b/tests/lora/test_chatglm3_tp.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List import vllm diff --git a/tests/lora/test_gemma.py b/tests/lora/test_gemma.py index 5ae705e47..8923aa221 100644 --- a/tests/lora/test_gemma.py +++ b/tests/lora/test_gemma.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List import pytest diff --git a/tests/lora/test_jamba.py b/tests/lora/test_jamba.py index 6aa33926c..c04174665 100644 --- a/tests/lora/test_jamba.py +++ b/tests/lora/test_jamba.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List import pytest diff --git a/tests/lora/test_layers.py b/tests/lora/test_layers.py index 08a589d7e..0838ca02c 100644 --- a/tests/lora/test_layers.py +++ b/tests/lora/test_layers.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import random from copy import deepcopy from dataclasses import dataclass diff --git a/tests/lora/test_llama_tp.py b/tests/lora/test_llama_tp.py index dfeac3809..39f779f40 100644 --- a/tests/lora/test_llama_tp.py +++ b/tests/lora/test_llama_tp.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List import ray diff --git a/tests/lora/test_long_context.py b/tests/lora/test_long_context.py index e7a34f2ce..62005de73 100644 --- a/tests/lora/test_long_context.py +++ b/tests/lora/test_long_context.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import ast from typing import List, Optional, Tuple diff --git a/tests/lora/test_lora_bias_e2e.py b/tests/lora/test_lora_bias_e2e.py index c2520c847..cbdd68831 100644 --- a/tests/lora/test_lora_bias_e2e.py +++ b/tests/lora/test_lora_bias_e2e.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List import pytest diff --git a/tests/lora/test_lora_checkpoints.py b/tests/lora/test_lora_checkpoints.py index b907af47d..d2a4b901b 100644 --- a/tests/lora/test_lora_checkpoints.py +++ b/tests/lora/test_lora_checkpoints.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List import pytest diff --git a/tests/lora/test_lora_huggingface.py b/tests/lora/test_lora_huggingface.py index 1c0ee01c0..273fe9ae0 100644 --- a/tests/lora/test_lora_huggingface.py +++ b/tests/lora/test_lora_huggingface.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List import pytest diff --git a/tests/lora/test_lora_manager.py b/tests/lora/test_lora_manager.py index 9a5b9aabf..6666f54fd 100644 --- a/tests/lora/test_lora_manager.py +++ b/tests/lora/test_lora_manager.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import os from typing import Dict, List diff --git a/tests/lora/test_minicpmv_tp.py b/tests/lora/test_minicpmv_tp.py index 3b0f18325..2e81bb326 100644 --- a/tests/lora/test_minicpmv_tp.py +++ b/tests/lora/test_minicpmv_tp.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List import pytest diff --git a/tests/lora/test_mixtral.py b/tests/lora/test_mixtral.py index 940a86522..90cf8fd39 100644 --- a/tests/lora/test_mixtral.py +++ b/tests/lora/test_mixtral.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List import pytest diff --git a/tests/lora/test_peft_helper.py b/tests/lora/test_peft_helper.py index a524d5ce5..9935472ad 100644 --- a/tests/lora/test_peft_helper.py +++ b/tests/lora/test_peft_helper.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import json import math import shutil diff --git a/tests/lora/test_phi.py b/tests/lora/test_phi.py index 5a3fcb8d6..651c89ffc 100644 --- a/tests/lora/test_phi.py +++ b/tests/lora/test_phi.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List import vllm diff --git a/tests/lora/test_punica_ops_sizes.py b/tests/lora/test_punica_ops_sizes.py index 433ca7577..ecd3bc497 100644 --- a/tests/lora/test_punica_ops_sizes.py +++ b/tests/lora/test_punica_ops_sizes.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """ This script is mainly used to tests various hidden_sizes. We have collected the hidden_sizes included in the LoRA models currently supported by vLLM. It tests diff --git a/tests/lora/test_punica_ops_variation.py b/tests/lora/test_punica_ops_variation.py index 2bb84c1cf..6d1d3c943 100644 --- a/tests/lora/test_punica_ops_variation.py +++ b/tests/lora/test_punica_ops_variation.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """ This script is mainly used to test whether trtion kernels can run normally under different conditions, including various batches, numbers of LoRA , and diff --git a/tests/lora/test_quant_model.py b/tests/lora/test_quant_model.py index 26bf770cc..5702aa26b 100644 --- a/tests/lora/test_quant_model.py +++ b/tests/lora/test_quant_model.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Adapted from # https://github.com/fmmoret/vllm/blob/fm-support-lora-on-quantized-models/tests/lora/test_llama.py from dataclasses import dataclass diff --git a/tests/lora/test_qwen2vl.py b/tests/lora/test_qwen2vl.py index 570aa3861..a988f06ab 100644 --- a/tests/lora/test_qwen2vl.py +++ b/tests/lora/test_qwen2vl.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List import pytest diff --git a/tests/lora/test_tokenizer_group.py b/tests/lora/test_tokenizer_group.py index d225a3f7d..589167e80 100644 --- a/tests/lora/test_tokenizer_group.py +++ b/tests/lora/test_tokenizer_group.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import pytest from transformers import AutoTokenizer, PreTrainedTokenizerBase diff --git a/tests/lora/test_utils.py b/tests/lora/test_utils.py index 85110b8fa..34a26e9ed 100644 --- a/tests/lora/test_utils.py +++ b/tests/lora/test_utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from collections import OrderedDict from unittest.mock import patch diff --git a/tests/lora/test_worker.py b/tests/lora/test_worker.py index 9d814f657..797141ea3 100644 --- a/tests/lora/test_worker.py +++ b/tests/lora/test_worker.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import os import random import tempfile diff --git a/tests/lora/utils.py b/tests/lora/utils.py index ce47546f2..bda00e081 100644 --- a/tests/lora/utils.py +++ b/tests/lora/utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Dict, List, Optional import torch diff --git a/tests/metrics/test_metrics.py b/tests/metrics/test_metrics.py index b3c785055..0942c8eed 100644 --- a/tests/metrics/test_metrics.py +++ b/tests/metrics/test_metrics.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import time from typing import List diff --git a/tests/model_executor/conftest.py b/tests/model_executor/conftest.py index 10792b0a0..b588a1a96 100644 --- a/tests/model_executor/conftest.py +++ b/tests/model_executor/conftest.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import pytest diff --git a/tests/model_executor/test_enabled_custom_ops.py b/tests/model_executor/test_enabled_custom_ops.py index 0a3aba255..2c6780848 100644 --- a/tests/model_executor/test_enabled_custom_ops.py +++ b/tests/model_executor/test_enabled_custom_ops.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List import pytest diff --git a/tests/model_executor/test_guided_processors.py b/tests/model_executor/test_guided_processors.py index be5282d9c..64d0928f8 100644 --- a/tests/model_executor/test_guided_processors.py +++ b/tests/model_executor/test_guided_processors.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import pickle import pytest diff --git a/tests/model_executor/test_model_load_with_params.py b/tests/model_executor/test_model_load_with_params.py index 9c1f784c1..760a11993 100644 --- a/tests/model_executor/test_model_load_with_params.py +++ b/tests/model_executor/test_model_load_with_params.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import os import pytest diff --git a/tests/model_executor/weight_utils.py b/tests/model_executor/weight_utils.py index c8b9bed69..11dfe4d49 100644 --- a/tests/model_executor/weight_utils.py +++ b/tests/model_executor/weight_utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import os import tempfile diff --git a/tests/models/decoder_only/audio_language/test_ultravox.py b/tests/models/decoder_only/audio_language/test_ultravox.py index 1e329dc4c..fe9361d12 100644 --- a/tests/models/decoder_only/audio_language/test_ultravox.py +++ b/tests/models/decoder_only/audio_language/test_ultravox.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List, Optional, Tuple, Type import numpy as np diff --git a/tests/models/decoder_only/language/test_aqlm.py b/tests/models/decoder_only/language/test_aqlm.py index a8cb5bbf9..85557b30d 100644 --- a/tests/models/decoder_only/language/test_aqlm.py +++ b/tests/models/decoder_only/language/test_aqlm.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Compare the outputs of a AQLM model between vLLM and HF Transformers Run `pytest tests/models/test_aqlm.py`. diff --git a/tests/models/decoder_only/language/test_fp8.py b/tests/models/decoder_only/language/test_fp8.py index 5f06f1e3a..6a0e148d5 100644 --- a/tests/models/decoder_only/language/test_fp8.py +++ b/tests/models/decoder_only/language/test_fp8.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # flake8: noqa """Tests fp8 models against ground truth generation Note: these tests will only pass on L4 GPU. diff --git a/tests/models/decoder_only/language/test_gguf.py b/tests/models/decoder_only/language/test_gguf.py index ad8f8a0c3..57fe1d5b1 100644 --- a/tests/models/decoder_only/language/test_gguf.py +++ b/tests/models/decoder_only/language/test_gguf.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """ Tests gguf models against unquantized models generations Note: To pass the test, quantization higher than Q4 should be used diff --git a/tests/models/decoder_only/language/test_gptq_marlin.py b/tests/models/decoder_only/language/test_gptq_marlin.py index 037411a18..0f61466c3 100644 --- a/tests/models/decoder_only/language/test_gptq_marlin.py +++ b/tests/models/decoder_only/language/test_gptq_marlin.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Compares the outputs of gptq vs gptq_marlin Note: GPTQ and Marlin do not have bitwise correctness. As a result, in this test, we just confirm that the top selected tokens of the diff --git a/tests/models/decoder_only/language/test_gptq_marlin_24.py b/tests/models/decoder_only/language/test_gptq_marlin_24.py index 26cb3ec31..c81626148 100644 --- a/tests/models/decoder_only/language/test_gptq_marlin_24.py +++ b/tests/models/decoder_only/language/test_gptq_marlin_24.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Compare the outputs of a GPTQ model to a Marlin_24 model. Note: GPTQ and Marlin_24 do not have bitwise correctness. diff --git a/tests/models/decoder_only/language/test_granite.py b/tests/models/decoder_only/language/test_granite.py index 5e93842f4..119b79d64 100644 --- a/tests/models/decoder_only/language/test_granite.py +++ b/tests/models/decoder_only/language/test_granite.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Compare the outputs of HF and vLLM for Granite models using greedy sampling. Run `pytest tests/models/test_granite.py`. diff --git a/tests/models/decoder_only/language/test_jamba.py b/tests/models/decoder_only/language/test_jamba.py index 2e06b10fb..cc98f1d7b 100644 --- a/tests/models/decoder_only/language/test_jamba.py +++ b/tests/models/decoder_only/language/test_jamba.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import pytest from tests.utils import multi_gpu_test diff --git a/tests/models/decoder_only/language/test_mamba.py b/tests/models/decoder_only/language/test_mamba.py index 1ad4f5aae..854f4fe4f 100644 --- a/tests/models/decoder_only/language/test_mamba.py +++ b/tests/models/decoder_only/language/test_mamba.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Compare the outputs of HF and vLLM when using greedy sampling for Mamba. Run `pytest tests/models/test_mamba.py`. diff --git a/tests/models/decoder_only/language/test_mistral.py b/tests/models/decoder_only/language/test_mistral.py index bdc157178..179236730 100644 --- a/tests/models/decoder_only/language/test_mistral.py +++ b/tests/models/decoder_only/language/test_mistral.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Compare the outputs of HF and vLLM for Mistral models using greedy sampling. Run `pytest tests/models/test_mistral.py`. diff --git a/tests/models/decoder_only/language/test_modelopt.py b/tests/models/decoder_only/language/test_modelopt.py index 077e50e3a..66dd97957 100644 --- a/tests/models/decoder_only/language/test_modelopt.py +++ b/tests/models/decoder_only/language/test_modelopt.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # flake8: noqa """Tests Model Optimizer fp8 models against ground truth generation Note: these tests will only pass on H100 diff --git a/tests/models/decoder_only/language/test_models.py b/tests/models/decoder_only/language/test_models.py index c7efa4edb..1ad562415 100644 --- a/tests/models/decoder_only/language/test_models.py +++ b/tests/models/decoder_only/language/test_models.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Compare the outputs of HF and vLLM when using greedy sampling. Run `pytest tests/models/test_models.py`. diff --git a/tests/models/decoder_only/language/test_phimoe.py b/tests/models/decoder_only/language/test_phimoe.py index c997359a2..f9757d6ac 100644 --- a/tests/models/decoder_only/language/test_phimoe.py +++ b/tests/models/decoder_only/language/test_phimoe.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Compare the outputs of HF and vLLM for moe models using greedy sampling. Run `pytest tests/models/test_phimoe.py`. diff --git a/tests/models/decoder_only/vision_language/test_awq.py b/tests/models/decoder_only/vision_language/test_awq.py index 18ceb34a4..31a5cd260 100644 --- a/tests/models/decoder_only/vision_language/test_awq.py +++ b/tests/models/decoder_only/vision_language/test_awq.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List, Optional, Type import pytest diff --git a/tests/models/decoder_only/vision_language/test_h2ovl.py b/tests/models/decoder_only/vision_language/test_h2ovl.py index 7406df253..9590adf6f 100644 --- a/tests/models/decoder_only/vision_language/test_h2ovl.py +++ b/tests/models/decoder_only/vision_language/test_h2ovl.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Optional, Tuple import pytest diff --git a/tests/models/decoder_only/vision_language/test_intern_vit.py b/tests/models/decoder_only/vision_language/test_intern_vit.py index 32fcb0bbc..a842d14fe 100644 --- a/tests/models/decoder_only/vision_language/test_intern_vit.py +++ b/tests/models/decoder_only/vision_language/test_intern_vit.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Optional import pytest diff --git a/tests/models/decoder_only/vision_language/test_models.py b/tests/models/decoder_only/vision_language/test_models.py index 62c644f73..e3cda8971 100644 --- a/tests/models/decoder_only/vision_language/test_models.py +++ b/tests/models/decoder_only/vision_language/test_models.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Common tests for testing .generate() functionality for single / multiple image, embedding, and video support for different VLMs in vLLM. """ diff --git a/tests/models/decoder_only/vision_language/test_phi3v.py b/tests/models/decoder_only/vision_language/test_phi3v.py index 3a8934adf..dd68fe4cd 100644 --- a/tests/models/decoder_only/vision_language/test_phi3v.py +++ b/tests/models/decoder_only/vision_language/test_phi3v.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import os import re from typing import List, Optional, Tuple, Type diff --git a/tests/models/decoder_only/vision_language/test_pixtral.py b/tests/models/decoder_only/vision_language/test_pixtral.py index 8103e5305..602da2b5f 100644 --- a/tests/models/decoder_only/vision_language/test_pixtral.py +++ b/tests/models/decoder_only/vision_language/test_pixtral.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Compare the outputs of HF and vLLM for Mistral models using greedy sampling. Run `pytest tests/models/test_mistral.py`. diff --git a/tests/models/decoder_only/vision_language/test_qwen2_vl.py b/tests/models/decoder_only/vision_language/test_qwen2_vl.py index 5a485f3d8..de240a904 100644 --- a/tests/models/decoder_only/vision_language/test_qwen2_vl.py +++ b/tests/models/decoder_only/vision_language/test_qwen2_vl.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Any, List, Optional, Tuple, Type, TypedDict, Union import numpy.typing as npt diff --git a/tests/models/decoder_only/vision_language/vlm_utils/builders.py b/tests/models/decoder_only/vision_language/vlm_utils/builders.py index 59773be70..539410d18 100644 --- a/tests/models/decoder_only/vision_language/vlm_utils/builders.py +++ b/tests/models/decoder_only/vision_language/vlm_utils/builders.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Helpers for building inputs that can be leveraged for different test types. """ from pathlib import PosixPath diff --git a/tests/models/decoder_only/vision_language/vlm_utils/case_filtering.py b/tests/models/decoder_only/vision_language/vlm_utils/case_filtering.py index 9bb713416..ca4ec2141 100644 --- a/tests/models/decoder_only/vision_language/vlm_utils/case_filtering.py +++ b/tests/models/decoder_only/vision_language/vlm_utils/case_filtering.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Utils for determining which subset of model tests belong to a specific modality, getting all combinations (similar to pytest's parametrization), handling multimodal placeholder substitution, and so on. diff --git a/tests/models/decoder_only/vision_language/vlm_utils/core.py b/tests/models/decoder_only/vision_language/vlm_utils/core.py index 54b7b0733..0aed26769 100644 --- a/tests/models/decoder_only/vision_language/vlm_utils/core.py +++ b/tests/models/decoder_only/vision_language/vlm_utils/core.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Core test implementation to be shared across modalities.""" from typing import Any, Callable, Dict, List, Optional, Tuple, Type, Union @@ -153,4 +154,4 @@ def process_runner_outputs( def process_outputs(output_processor, model, outputs_per_image): """Applies a model specific post-processor function to a runner's output""" return [[output_processor(res, model) for res in outputs] - for outputs in outputs_per_image] \ No newline at end of file + for outputs in outputs_per_image] diff --git a/tests/models/decoder_only/vision_language/vlm_utils/custom_inputs.py b/tests/models/decoder_only/vision_language/vlm_utils/custom_inputs.py index 2291f4fa0..2f03a114a 100644 --- a/tests/models/decoder_only/vision_language/vlm_utils/custom_inputs.py +++ b/tests/models/decoder_only/vision_language/vlm_utils/custom_inputs.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Custom input builders for edge-cases in different models.""" from typing import Callable diff --git a/tests/models/decoder_only/vision_language/vlm_utils/model_utils.py b/tests/models/decoder_only/vision_language/vlm_utils/model_utils.py index 07bdb2cee..b0a88161c 100644 --- a/tests/models/decoder_only/vision_language/vlm_utils/model_utils.py +++ b/tests/models/decoder_only/vision_language/vlm_utils/model_utils.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Common utility functions relating to different models that are useful for manipulating the input / output of HF & vLLM test runners, which are typically specific to a small subset of models. diff --git a/tests/models/decoder_only/vision_language/vlm_utils/runners.py b/tests/models/decoder_only/vision_language/vlm_utils/runners.py index 2d3b39fe3..fb9df37ca 100644 --- a/tests/models/decoder_only/vision_language/vlm_utils/runners.py +++ b/tests/models/decoder_only/vision_language/vlm_utils/runners.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Entrypoints for wrapping the core run_test implementation for specific test types / modalities. """ diff --git a/tests/models/decoder_only/vision_language/vlm_utils/types.py b/tests/models/decoder_only/vision_language/vlm_utils/types.py index e2e0c6390..ae3b9d59b 100644 --- a/tests/models/decoder_only/vision_language/vlm_utils/types.py +++ b/tests/models/decoder_only/vision_language/vlm_utils/types.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Types for writing multimodal model tests.""" from enum import Enum from pathlib import PosixPath diff --git a/tests/models/embedding/language/test_cls_models.py b/tests/models/embedding/language/test_cls_models.py index 0cbe4afe9..b0420ff5c 100644 --- a/tests/models/embedding/language/test_cls_models.py +++ b/tests/models/embedding/language/test_cls_models.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Compare the classification outputs of HF and vLLM models. Run `pytest tests/models/test_cls_models.py`. diff --git a/tests/models/embedding/language/test_embedding.py b/tests/models/embedding/language/test_embedding.py index e17198e38..ad6385376 100644 --- a/tests/models/embedding/language/test_embedding.py +++ b/tests/models/embedding/language/test_embedding.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Compare the embedding outputs of HF and vLLM models. Run `pytest tests/models/embedding/language/test_embedding.py`. diff --git a/tests/models/embedding/language/test_gritlm.py b/tests/models/embedding/language/test_gritlm.py index 55c2e5d4e..7ed2fb8a6 100644 --- a/tests/models/embedding/language/test_gritlm.py +++ b/tests/models/embedding/language/test_gritlm.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import importlib.util import math from array import array diff --git a/tests/models/embedding/language/test_scoring.py b/tests/models/embedding/language/test_scoring.py index 3db27d942..d6408258f 100644 --- a/tests/models/embedding/language/test_scoring.py +++ b/tests/models/embedding/language/test_scoring.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Compare the scoring outputs of HF and vLLM models. Run `pytest tests/models/embedding/language/test_scoring.py`. diff --git a/tests/models/embedding/utils.py b/tests/models/embedding/utils.py index f96c7d2b1..567aa5098 100644 --- a/tests/models/embedding/utils.py +++ b/tests/models/embedding/utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List, Sequence import torch diff --git a/tests/models/embedding/vision_language/test_dse_qwen2_vl.py b/tests/models/embedding/vision_language/test_dse_qwen2_vl.py index 2641987b2..82f2bf531 100644 --- a/tests/models/embedding/vision_language/test_dse_qwen2_vl.py +++ b/tests/models/embedding/vision_language/test_dse_qwen2_vl.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from functools import partial from typing import Callable, Dict, List, Type diff --git a/tests/models/embedding/vision_language/test_llava_next.py b/tests/models/embedding/vision_language/test_llava_next.py index f4cd8b81a..6ba3c5403 100644 --- a/tests/models/embedding/vision_language/test_llava_next.py +++ b/tests/models/embedding/vision_language/test_llava_next.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List, Type import pytest diff --git a/tests/models/embedding/vision_language/test_phi3v.py b/tests/models/embedding/vision_language/test_phi3v.py index 9374c23dd..0cb948746 100644 --- a/tests/models/embedding/vision_language/test_phi3v.py +++ b/tests/models/embedding/vision_language/test_phi3v.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List, Type import pytest diff --git a/tests/models/encoder_decoder/audio_language/test_whisper.py b/tests/models/encoder_decoder/audio_language/test_whisper.py index eb238c533..80d6897da 100644 --- a/tests/models/encoder_decoder/audio_language/test_whisper.py +++ b/tests/models/encoder_decoder/audio_language/test_whisper.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Compare the outputs of HF and vLLM for Whisper models using greedy sampling. Run `pytest tests/models/encoder_decoder/audio/test_whisper.py`. diff --git a/tests/models/encoder_decoder/language/test_bart.py b/tests/models/encoder_decoder/language/test_bart.py index 10aba8427..81b629fdc 100644 --- a/tests/models/encoder_decoder/language/test_bart.py +++ b/tests/models/encoder_decoder/language/test_bart.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Compare the outputs of HF and vLLM for BART models using greedy sampling. Run `pytest tests/models/encoder_decoder/language/test_bart.py`. diff --git a/tests/models/encoder_decoder/vision_language/test_broadcast.py b/tests/models/encoder_decoder/vision_language/test_broadcast.py index 542f41a38..8d986414e 100644 --- a/tests/models/encoder_decoder/vision_language/test_broadcast.py +++ b/tests/models/encoder_decoder/vision_language/test_broadcast.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import pytest from ....utils import multi_gpu_test diff --git a/tests/models/encoder_decoder/vision_language/test_florence2.py b/tests/models/encoder_decoder/vision_language/test_florence2.py index d686f1da3..a1d156799 100644 --- a/tests/models/encoder_decoder/vision_language/test_florence2.py +++ b/tests/models/encoder_decoder/vision_language/test_florence2.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from functools import partial from typing import List, Optional, Tuple, Type diff --git a/tests/models/encoder_decoder/vision_language/test_mllama.py b/tests/models/encoder_decoder/vision_language/test_mllama.py index 16c71228e..4cd2dbdb4 100644 --- a/tests/models/encoder_decoder/vision_language/test_mllama.py +++ b/tests/models/encoder_decoder/vision_language/test_mllama.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List, Optional, Tuple, Type, overload import pytest diff --git a/tests/models/multimodal/processing/test_common.py b/tests/models/multimodal/processing/test_common.py index ca28da268..3921d4e19 100644 --- a/tests/models/multimodal/processing/test_common.py +++ b/tests/models/multimodal/processing/test_common.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from functools import partial import numpy as np diff --git a/tests/models/multimodal/processing/test_idefics3.py b/tests/models/multimodal/processing/test_idefics3.py index 69b91ad4a..00c1dae51 100644 --- a/tests/models/multimodal/processing/test_idefics3.py +++ b/tests/models/multimodal/processing/test_idefics3.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Tests for Idefics3's multimodal preprocessing kwargs.""" from typing import Optional diff --git a/tests/models/multimodal/processing/test_internvl.py b/tests/models/multimodal/processing/test_internvl.py index d6c60595c..0d921e9d3 100644 --- a/tests/models/multimodal/processing/test_internvl.py +++ b/tests/models/multimodal/processing/test_internvl.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Tests for InternVL's multimodal preprocessing kwargs.""" from typing import Callable, Optional diff --git a/tests/models/multimodal/processing/test_llava_next.py b/tests/models/multimodal/processing/test_llava_next.py index 6de649f87..d2497e62d 100644 --- a/tests/models/multimodal/processing/test_llava_next.py +++ b/tests/models/multimodal/processing/test_llava_next.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import itertools from functools import partial diff --git a/tests/models/multimodal/processing/test_llava_onevision.py b/tests/models/multimodal/processing/test_llava_onevision.py index 806437d35..bd4dbd46d 100644 --- a/tests/models/multimodal/processing/test_llava_onevision.py +++ b/tests/models/multimodal/processing/test_llava_onevision.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import itertools from functools import partial diff --git a/tests/models/multimodal/processing/test_phi3v.py b/tests/models/multimodal/processing/test_phi3v.py index 7f82a8f18..44edec457 100644 --- a/tests/models/multimodal/processing/test_phi3v.py +++ b/tests/models/multimodal/processing/test_phi3v.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Tests for phi3v's multimodal preprocessing kwargs.""" import pytest diff --git a/tests/models/multimodal/processing/test_qwen2_vl.py b/tests/models/multimodal/processing/test_qwen2_vl.py index de14fbbff..47c9b0add 100644 --- a/tests/models/multimodal/processing/test_qwen2_vl.py +++ b/tests/models/multimodal/processing/test_qwen2_vl.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import pytest from vllm.multimodal import MULTIMODAL_REGISTRY diff --git a/tests/models/registry.py b/tests/models/registry.py index 7952e65aa..d0dbbf00e 100644 --- a/tests/models/registry.py +++ b/tests/models/registry.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from dataclasses import dataclass, field from typing import AbstractSet, Any, Literal, Mapping, Optional diff --git a/tests/models/test_initialization.py b/tests/models/test_initialization.py index d3a3aaf67..64928a65d 100644 --- a/tests/models/test_initialization.py +++ b/tests/models/test_initialization.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from unittest.mock import patch import pytest diff --git a/tests/models/test_oot_registration.py b/tests/models/test_oot_registration.py index 2c413a633..ef665baa1 100644 --- a/tests/models/test_oot_registration.py +++ b/tests/models/test_oot_registration.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import os import pytest diff --git a/tests/models/test_registry.py b/tests/models/test_registry.py index ac0366847..80d3f78f9 100644 --- a/tests/models/test_registry.py +++ b/tests/models/test_registry.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import warnings import pytest diff --git a/tests/models/utils.py b/tests/models/utils.py index 0eb3f61f1..e2be43c12 100644 --- a/tests/models/utils.py +++ b/tests/models/utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import warnings from typing import Dict, List, Optional, Sequence, Tuple, Union diff --git a/tests/mq_llm_engine/test_abort.py b/tests/mq_llm_engine/test_abort.py index 782b508a5..808346b5e 100644 --- a/tests/mq_llm_engine/test_abort.py +++ b/tests/mq_llm_engine/test_abort.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Test that aborting is handled properly.""" import asyncio diff --git a/tests/mq_llm_engine/test_error_handling.py b/tests/mq_llm_engine/test_error_handling.py index 83bc4e7cf..35d001781 100644 --- a/tests/mq_llm_engine/test_error_handling.py +++ b/tests/mq_llm_engine/test_error_handling.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Test that various errors are handled properly.""" import asyncio diff --git a/tests/mq_llm_engine/test_load.py b/tests/mq_llm_engine/test_load.py index 630c112d0..2069ff987 100644 --- a/tests/mq_llm_engine/test_load.py +++ b/tests/mq_llm_engine/test_load.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Test that the MQLLMEngine is able to handle 10k concurrent requests.""" import asyncio diff --git a/tests/mq_llm_engine/utils.py b/tests/mq_llm_engine/utils.py index f717c1355..11e44f12b 100644 --- a/tests/mq_llm_engine/utils.py +++ b/tests/mq_llm_engine/utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import asyncio import multiprocessing from typing import Callable, Tuple, Union diff --git a/tests/multi_step/test_correctness_async_llm.py b/tests/multi_step/test_correctness_async_llm.py index b8524ed83..9822cee14 100644 --- a/tests/multi_step/test_correctness_async_llm.py +++ b/tests/multi_step/test_correctness_async_llm.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Test the AsyncLLMEngine with multi-step-decoding from typing import List, Optional diff --git a/tests/multi_step/test_correctness_llm.py b/tests/multi_step/test_correctness_llm.py index 34030d9d6..29d5ffd4c 100644 --- a/tests/multi_step/test_correctness_llm.py +++ b/tests/multi_step/test_correctness_llm.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Test the LLMEngine with multi-step-decoding import copy diff --git a/tests/multimodal/test_inputs.py b/tests/multimodal/test_inputs.py index 678bbb52b..f5d3e282f 100644 --- a/tests/multimodal/test_inputs.py +++ b/tests/multimodal/test_inputs.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import torch from vllm.multimodal.inputs import MultiModalKwargs, NestedTensors diff --git a/tests/multimodal/test_processing.py b/tests/multimodal/test_processing.py index 13f820d01..6cccd2aa2 100644 --- a/tests/multimodal/test_processing.py +++ b/tests/multimodal/test_processing.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from contextlib import nullcontext from typing import cast from unittest.mock import MagicMock diff --git a/tests/multimodal/test_processor_kwargs.py b/tests/multimodal/test_processor_kwargs.py index d141cdf1f..5d18b2ed7 100644 --- a/tests/multimodal/test_processor_kwargs.py +++ b/tests/multimodal/test_processor_kwargs.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from array import array from typing import Callable, Dict, Mapping, Optional from unittest.mock import patch diff --git a/tests/multimodal/test_utils.py b/tests/multimodal/test_utils.py index 198344e5b..f9e0f507a 100644 --- a/tests/multimodal/test_utils.py +++ b/tests/multimodal/test_utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import base64 import mimetypes import os diff --git a/tests/multimodal/utils.py b/tests/multimodal/utils.py index 29aeca605..9a336b7e6 100644 --- a/tests/multimodal/utils.py +++ b/tests/multimodal/utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import numpy as np from PIL import Image diff --git a/tests/neuron/test_prefix_prefill.py b/tests/neuron/test_prefix_prefill.py index 77b707a73..dfbcfc15e 100644 --- a/tests/neuron/test_prefix_prefill.py +++ b/tests/neuron/test_prefix_prefill.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import random from typing import Optional diff --git a/tests/plugins/vllm_add_dummy_model/setup.py b/tests/plugins/vllm_add_dummy_model/setup.py index 9b535127f..e3fb6efb2 100644 --- a/tests/plugins/vllm_add_dummy_model/setup.py +++ b/tests/plugins/vllm_add_dummy_model/setup.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from setuptools import setup setup(name='vllm_add_dummy_model', diff --git a/tests/plugins/vllm_add_dummy_model/vllm_add_dummy_model/__init__.py b/tests/plugins/vllm_add_dummy_model/vllm_add_dummy_model/__init__.py index 62a8f871f..0c431cb39 100644 --- a/tests/plugins/vllm_add_dummy_model/vllm_add_dummy_model/__init__.py +++ b/tests/plugins/vllm_add_dummy_model/vllm_add_dummy_model/__init__.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from vllm import ModelRegistry diff --git a/tests/plugins/vllm_add_dummy_model/vllm_add_dummy_model/my_gemma_embedding.py b/tests/plugins/vllm_add_dummy_model/vllm_add_dummy_model/my_gemma_embedding.py index 5e7d7d187..3af62b288 100644 --- a/tests/plugins/vllm_add_dummy_model/vllm_add_dummy_model/my_gemma_embedding.py +++ b/tests/plugins/vllm_add_dummy_model/vllm_add_dummy_model/my_gemma_embedding.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Iterable, List, Optional, Tuple, Union import torch diff --git a/tests/plugins/vllm_add_dummy_model/vllm_add_dummy_model/my_llava.py b/tests/plugins/vllm_add_dummy_model/vllm_add_dummy_model/my_llava.py index ac64edfd4..c23ab6430 100644 --- a/tests/plugins/vllm_add_dummy_model/vllm_add_dummy_model/my_llava.py +++ b/tests/plugins/vllm_add_dummy_model/vllm_add_dummy_model/my_llava.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Optional import torch diff --git a/tests/plugins/vllm_add_dummy_model/vllm_add_dummy_model/my_opt.py b/tests/plugins/vllm_add_dummy_model/vllm_add_dummy_model/my_opt.py index 569ef216c..bbd11ed4a 100644 --- a/tests/plugins/vllm_add_dummy_model/vllm_add_dummy_model/my_opt.py +++ b/tests/plugins/vllm_add_dummy_model/vllm_add_dummy_model/my_opt.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Optional import torch diff --git a/tests/plugins/vllm_add_dummy_platform/setup.py b/tests/plugins/vllm_add_dummy_platform/setup.py index 316399068..10df0b5e0 100644 --- a/tests/plugins/vllm_add_dummy_platform/setup.py +++ b/tests/plugins/vllm_add_dummy_platform/setup.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from setuptools import setup setup( diff --git a/tests/plugins/vllm_add_dummy_platform/vllm_add_dummy_platform/__init__.py b/tests/plugins/vllm_add_dummy_platform/vllm_add_dummy_platform/__init__.py index 594cef520..0d1b062ac 100644 --- a/tests/plugins/vllm_add_dummy_platform/vllm_add_dummy_platform/__init__.py +++ b/tests/plugins/vllm_add_dummy_platform/vllm_add_dummy_platform/__init__.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Optional diff --git a/tests/plugins/vllm_add_dummy_platform/vllm_add_dummy_platform/dummy_attention_backend.py b/tests/plugins/vllm_add_dummy_platform/vllm_add_dummy_platform/dummy_attention_backend.py index 5634be3c8..33425bbc1 100644 --- a/tests/plugins/vllm_add_dummy_platform/vllm_add_dummy_platform/dummy_attention_backend.py +++ b/tests/plugins/vllm_add_dummy_platform/vllm_add_dummy_platform/dummy_attention_backend.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from vllm.attention.backends.flash_attn import FlashAttentionBackend diff --git a/tests/plugins/vllm_add_dummy_platform/vllm_add_dummy_platform/dummy_platform.py b/tests/plugins/vllm_add_dummy_platform/vllm_add_dummy_platform/dummy_platform.py index d7c6bdd70..5cefafc7e 100644 --- a/tests/plugins/vllm_add_dummy_platform/vllm_add_dummy_platform/dummy_platform.py +++ b/tests/plugins/vllm_add_dummy_platform/vllm_add_dummy_platform/dummy_platform.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from vllm.platforms.cuda import CudaPlatform diff --git a/tests/plugins_tests/test_platform_plugins.py b/tests/plugins_tests/test_platform_plugins.py index 661aa5f64..ed50fe535 100644 --- a/tests/plugins_tests/test_platform_plugins.py +++ b/tests/plugins_tests/test_platform_plugins.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import torch from tests.kernels.utils import override_backend_env_variable diff --git a/tests/prefix_caching/test_disable_sliding_window.py b/tests/prefix_caching/test_disable_sliding_window.py index 5a28943b7..19f393e07 100644 --- a/tests/prefix_caching/test_disable_sliding_window.py +++ b/tests/prefix_caching/test_disable_sliding_window.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Compare the with and without prefix caching. Run `pytest tests/prefix_caching/test_prefix_caching.py`. diff --git a/tests/prefix_caching/test_prefix_caching.py b/tests/prefix_caching/test_prefix_caching.py index 8d16710f1..90d424fe3 100644 --- a/tests/prefix_caching/test_prefix_caching.py +++ b/tests/prefix_caching/test_prefix_caching.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Compare the with and without prefix caching. Run `pytest tests/prefix_caching/test_prefix_caching.py`. diff --git a/tests/prompt_adapter/test_bloom.py b/tests/prompt_adapter/test_bloom.py index 6528b3009..a31d8e873 100644 --- a/tests/prompt_adapter/test_bloom.py +++ b/tests/prompt_adapter/test_bloom.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import pytest import vllm diff --git a/tests/prompt_adapter/test_multi_adapter_inference.py b/tests/prompt_adapter/test_multi_adapter_inference.py index 39a79becd..e249a6e64 100644 --- a/tests/prompt_adapter/test_multi_adapter_inference.py +++ b/tests/prompt_adapter/test_multi_adapter_inference.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from vllm import EngineArgs, LLMEngine, SamplingParams from vllm.prompt_adapter.request import PromptAdapterRequest diff --git a/tests/prompt_adapter/test_pa_lora.py b/tests/prompt_adapter/test_pa_lora.py index 2a5f23f7f..fb4c3e149 100644 --- a/tests/prompt_adapter/test_pa_lora.py +++ b/tests/prompt_adapter/test_pa_lora.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from huggingface_hub import snapshot_download from vllm import EngineArgs, LLMEngine, SamplingParams diff --git a/tests/quantization/test_bitsandbytes.py b/tests/quantization/test_bitsandbytes.py index 569fc8dfb..4b5210cdf 100644 --- a/tests/quantization/test_bitsandbytes.py +++ b/tests/quantization/test_bitsandbytes.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 '''Tests whether bitsandbytes computation is enabled correctly. Run `pytest tests/quantization/test_bitsandbytes.py`. diff --git a/tests/quantization/test_compressed_tensors.py b/tests/quantization/test_compressed_tensors.py index 1072697ec..7e2e6f6ed 100644 --- a/tests/quantization/test_compressed_tensors.py +++ b/tests/quantization/test_compressed_tensors.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Test model set-up and weight loading for llmcompressor-quantized models. Run `pytest tests/quantization/test_compressed_tensors.py`. diff --git a/tests/quantization/test_configs.py b/tests/quantization/test_configs.py index cf77ccec7..0abbd8ebb 100644 --- a/tests/quantization/test_configs.py +++ b/tests/quantization/test_configs.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Tests whether Marlin models can be loaded from the autogptq config. Run `pytest tests/quantization/test_configs.py --forked`. diff --git a/tests/quantization/test_cpu_offload.py b/tests/quantization/test_cpu_offload.py index 21ce5174c..29a5721ef 100644 --- a/tests/quantization/test_cpu_offload.py +++ b/tests/quantization/test_cpu_offload.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Expanded quantized model tests for CPU offloading # Base tests: tests/basic_correctness/test_cpu_offload.py diff --git a/tests/quantization/test_experts_int8.py b/tests/quantization/test_experts_int8.py index ec31c94ef..b6db6d5f2 100644 --- a/tests/quantization/test_experts_int8.py +++ b/tests/quantization/test_experts_int8.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # flake8: noqa """Tests experts_int8 quantization startup and generation, doesn't test correctness diff --git a/tests/quantization/test_fp8.py b/tests/quantization/test_fp8.py index 4bff73474..5616935eb 100644 --- a/tests/quantization/test_fp8.py +++ b/tests/quantization/test_fp8.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Tests whether FP8 computation is enabled correctly. Run `pytest tests/quantization/test_fp8.py --forked`. diff --git a/tests/quantization/test_ipex_quant.py b/tests/quantization/test_ipex_quant.py index 68a73f0f8..0e3913676 100644 --- a/tests/quantization/test_ipex_quant.py +++ b/tests/quantization/test_ipex_quant.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Test model set-up and inference for quantized HF models supported on the CPU/GPU backend using IPEX (including AWQ/GPTQ). diff --git a/tests/quantization/test_lm_head.py b/tests/quantization/test_lm_head.py index fa2d9645e..ec60d8a57 100644 --- a/tests/quantization/test_lm_head.py +++ b/tests/quantization/test_lm_head.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Tests whether gptq models with quantized lm_head can be loaded. Run `pytest tests/quantization/test_quant_lm_head_true.py --forked`. diff --git a/tests/quantization/test_quark.py b/tests/quantization/test_quark.py index 11382ad70..491370c7c 100644 --- a/tests/quantization/test_quark.py +++ b/tests/quantization/test_quark.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Test model set-up and weight loading for quark-quantized models. Run `pytest tests/quantization/test_quark.py`. diff --git a/tests/quantization/test_register_quantization_config.py b/tests/quantization/test_register_quantization_config.py index 8e7f44a39..9e1867f91 100644 --- a/tests/quantization/test_register_quantization_config.py +++ b/tests/quantization/test_register_quantization_config.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Tests register custom quantization config. See https://github.com/vllm-project/vllm/issues/11926 for more details. diff --git a/tests/quantization/utils.py b/tests/quantization/utils.py index 8ebd8dd2b..7a339c162 100644 --- a/tests/quantization/utils.py +++ b/tests/quantization/utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from vllm.model_executor.layers.quantization import get_quantization_config from vllm.platforms import current_platform diff --git a/tests/runai_model_streamer/test_runai_model_streamer_loader.py b/tests/runai_model_streamer/test_runai_model_streamer_loader.py index c5722fbae..aa91fa8e1 100644 --- a/tests/runai_model_streamer/test_runai_model_streamer_loader.py +++ b/tests/runai_model_streamer/test_runai_model_streamer_loader.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from vllm import SamplingParams from vllm.config import LoadConfig, LoadFormat from vllm.model_executor.model_loader.loader import (RunaiModelStreamerLoader, diff --git a/tests/runai_model_streamer/test_weight_utils.py b/tests/runai_model_streamer/test_weight_utils.py index 5c89bd78a..4afa76c51 100644 --- a/tests/runai_model_streamer/test_weight_utils.py +++ b/tests/runai_model_streamer/test_weight_utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import glob import tempfile diff --git a/tests/samplers/test_beam_search.py b/tests/samplers/test_beam_search.py index 4d1a6978d..39feb1895 100644 --- a/tests/samplers/test_beam_search.py +++ b/tests/samplers/test_beam_search.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Compare the outputs of HF and vLLM when using beam search. Run `pytest tests/samplers/test_beam_search.py`. diff --git a/tests/samplers/test_ignore_eos.py b/tests/samplers/test_ignore_eos.py index dc2482d85..7f26698c9 100644 --- a/tests/samplers/test_ignore_eos.py +++ b/tests/samplers/test_ignore_eos.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Make sure ignore_eos works. Run `pytest tests/samplers/test_ignore_eos.py`. diff --git a/tests/samplers/test_logits_processor.py b/tests/samplers/test_logits_processor.py index 297947012..3b95b0389 100644 --- a/tests/samplers/test_logits_processor.py +++ b/tests/samplers/test_logits_processor.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import pytest import torch diff --git a/tests/samplers/test_logprobs.py b/tests/samplers/test_logprobs.py index c07c71e38..59d36099c 100644 --- a/tests/samplers/test_logprobs.py +++ b/tests/samplers/test_logprobs.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List import pytest diff --git a/tests/samplers/test_no_bad_words.py b/tests/samplers/test_no_bad_words.py index 4190cf7cd..cc6557694 100644 --- a/tests/samplers/test_no_bad_words.py +++ b/tests/samplers/test_no_bad_words.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Make sure bad_words works. Run `pytest tests/samplers/test_no_bad_words.py`. diff --git a/tests/samplers/test_ranks.py b/tests/samplers/test_ranks.py index ed2fee1ae..c74c1c02c 100644 --- a/tests/samplers/test_ranks.py +++ b/tests/samplers/test_ranks.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import pytest from vllm import SamplingParams diff --git a/tests/samplers/test_rejection_sampler.py b/tests/samplers/test_rejection_sampler.py index dcb1b27bf..cc199bf68 100644 --- a/tests/samplers/test_rejection_sampler.py +++ b/tests/samplers/test_rejection_sampler.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Tests for rejection sampling.""" from typing import List, Tuple diff --git a/tests/samplers/test_sampler.py b/tests/samplers/test_sampler.py index 28c34064f..ca09e536a 100644 --- a/tests/samplers/test_sampler.py +++ b/tests/samplers/test_sampler.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import itertools import random from dataclasses import dataclass diff --git a/tests/samplers/test_seeded_generate.py b/tests/samplers/test_seeded_generate.py index bf1ee6c39..4e8282561 100644 --- a/tests/samplers/test_seeded_generate.py +++ b/tests/samplers/test_seeded_generate.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Verify that seeded random sampling is deterministic. Run `pytest tests/samplers/test_seeded_generate.py`. diff --git a/tests/samplers/test_typical_acceptance_sampler.py b/tests/samplers/test_typical_acceptance_sampler.py index 4ddad66dc..ecf98179c 100644 --- a/tests/samplers/test_typical_acceptance_sampler.py +++ b/tests/samplers/test_typical_acceptance_sampler.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Tests for rejection sampling.""" import pytest diff --git a/tests/spec_decode/e2e/conftest.py b/tests/spec_decode/e2e/conftest.py index 5cb982a08..53c888816 100644 --- a/tests/spec_decode/e2e/conftest.py +++ b/tests/spec_decode/e2e/conftest.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from itertools import cycle from typing import List, Optional, Sequence, Tuple, Union diff --git a/tests/spec_decode/e2e/test_compatibility.py b/tests/spec_decode/e2e/test_compatibility.py index af8397c23..14a0ebf1d 100644 --- a/tests/spec_decode/e2e/test_compatibility.py +++ b/tests/spec_decode/e2e/test_compatibility.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import pytest from vllm import SamplingParams diff --git a/tests/spec_decode/e2e/test_eagle_correctness.py b/tests/spec_decode/e2e/test_eagle_correctness.py index 5bc70de9d..6d1803f8b 100644 --- a/tests/spec_decode/e2e/test_eagle_correctness.py +++ b/tests/spec_decode/e2e/test_eagle_correctness.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """This docstring details important information on the testing methodology. Most of the tests rely on "greedy equality", where we expect the output of diff --git a/tests/spec_decode/e2e/test_integration.py b/tests/spec_decode/e2e/test_integration.py index b89e58497..c67fa8514 100644 --- a/tests/spec_decode/e2e/test_integration.py +++ b/tests/spec_decode/e2e/test_integration.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Tests which cover integration of the speculative decoding framework with other features, e.g. cuda graphs. """ diff --git a/tests/spec_decode/e2e/test_integration_dist_tp2.py b/tests/spec_decode/e2e/test_integration_dist_tp2.py index 7001ee4c0..e5a542b6d 100644 --- a/tests/spec_decode/e2e/test_integration_dist_tp2.py +++ b/tests/spec_decode/e2e/test_integration_dist_tp2.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Tests which cover integration of the speculative decoding framework with tensor parallelism. """ diff --git a/tests/spec_decode/e2e/test_integration_dist_tp4.py b/tests/spec_decode/e2e/test_integration_dist_tp4.py index 2cb10de1c..cb9c46dc7 100644 --- a/tests/spec_decode/e2e/test_integration_dist_tp4.py +++ b/tests/spec_decode/e2e/test_integration_dist_tp4.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Tests which cover integration of the speculative decoding framework with tensor parallelism. """ diff --git a/tests/spec_decode/e2e/test_logprobs.py b/tests/spec_decode/e2e/test_logprobs.py index 1a543606c..5991a8b02 100644 --- a/tests/spec_decode/e2e/test_logprobs.py +++ b/tests/spec_decode/e2e/test_logprobs.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from itertools import cycle import pytest diff --git a/tests/spec_decode/e2e/test_medusa_correctness.py b/tests/spec_decode/e2e/test_medusa_correctness.py index dbcbc0db1..807f41cc9 100644 --- a/tests/spec_decode/e2e/test_medusa_correctness.py +++ b/tests/spec_decode/e2e/test_medusa_correctness.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """This docstring details important information on the testing methodology. Most of the tests rely on "greedy equality", where we expect the output of diff --git a/tests/spec_decode/e2e/test_mlp_correctness.py b/tests/spec_decode/e2e/test_mlp_correctness.py index 1fa1104f5..a2b84b902 100644 --- a/tests/spec_decode/e2e/test_mlp_correctness.py +++ b/tests/spec_decode/e2e/test_mlp_correctness.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """This docstring details important information on the testing methodology. Most of the tests rely on "greedy equality", where we expect the output of diff --git a/tests/spec_decode/e2e/test_multistep_correctness.py b/tests/spec_decode/e2e/test_multistep_correctness.py index 05ad468dd..d396e52a9 100644 --- a/tests/spec_decode/e2e/test_multistep_correctness.py +++ b/tests/spec_decode/e2e/test_multistep_correctness.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """The tests in this file verify end-to-end speculative decoding correctness. This docstring details important information on the testing methodology. diff --git a/tests/spec_decode/e2e/test_ngram_correctness.py b/tests/spec_decode/e2e/test_ngram_correctness.py index 77f8b8998..1aff53cb5 100644 --- a/tests/spec_decode/e2e/test_ngram_correctness.py +++ b/tests/spec_decode/e2e/test_ngram_correctness.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """This docstring details important information on the testing methodology. Most of the tests rely on "greedy equality", where we expect the output of diff --git a/tests/spec_decode/e2e/test_seed.py b/tests/spec_decode/e2e/test_seed.py index e42cf416b..b7d279f29 100644 --- a/tests/spec_decode/e2e/test_seed.py +++ b/tests/spec_decode/e2e/test_seed.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import pytest from .conftest import run_equality_correctness_test diff --git a/tests/spec_decode/test_batch_expansion.py b/tests/spec_decode/test_batch_expansion.py index 3504fcf43..fe95ff9b9 100644 --- a/tests/spec_decode/test_batch_expansion.py +++ b/tests/spec_decode/test_batch_expansion.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List import pytest diff --git a/tests/spec_decode/test_dynamic_spec_decode.py b/tests/spec_decode/test_dynamic_spec_decode.py index aa49a3aee..0bff0ea1d 100644 --- a/tests/spec_decode/test_dynamic_spec_decode.py +++ b/tests/spec_decode/test_dynamic_spec_decode.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from unittest.mock import MagicMock, patch import pytest diff --git a/tests/spec_decode/test_metrics.py b/tests/spec_decode/test_metrics.py index 7477486a3..1a6693e16 100644 --- a/tests/spec_decode/test_metrics.py +++ b/tests/spec_decode/test_metrics.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import math from unittest.mock import MagicMock diff --git a/tests/spec_decode/test_multi_step_worker.py b/tests/spec_decode/test_multi_step_worker.py index 0b5d82b66..2bf401613 100644 --- a/tests/spec_decode/test_multi_step_worker.py +++ b/tests/spec_decode/test_multi_step_worker.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import random from typing import Dict, List from unittest.mock import MagicMock diff --git a/tests/spec_decode/test_ngram_worker.py b/tests/spec_decode/test_ngram_worker.py index f66e95718..7de54b3ed 100644 --- a/tests/spec_decode/test_ngram_worker.py +++ b/tests/spec_decode/test_ngram_worker.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import torch from vllm.sequence import ExecuteModelRequest diff --git a/tests/spec_decode/test_scorer.py b/tests/spec_decode/test_scorer.py index 5a093dea1..7bbbb0236 100644 --- a/tests/spec_decode/test_scorer.py +++ b/tests/spec_decode/test_scorer.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import random from typing import List diff --git a/tests/spec_decode/test_spec_decode_worker.py b/tests/spec_decode/test_spec_decode_worker.py index d8c3af4c1..eee0f4c89 100644 --- a/tests/spec_decode/test_spec_decode_worker.py +++ b/tests/spec_decode/test_spec_decode_worker.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import random from collections import defaultdict from types import SimpleNamespace diff --git a/tests/spec_decode/test_utils.py b/tests/spec_decode/test_utils.py index 195fce648..24573e224 100644 --- a/tests/spec_decode/test_utils.py +++ b/tests/spec_decode/test_utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from unittest.mock import MagicMock import pytest diff --git a/tests/spec_decode/utils.py b/tests/spec_decode/utils.py index 2f883c2ff..38f57e99b 100644 --- a/tests/spec_decode/utils.py +++ b/tests/spec_decode/utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from itertools import count from typing import Callable, Dict, List, Optional from typing import Sequence as GenericSequence diff --git a/tests/standalone_tests/lazy_torch_compile.py b/tests/standalone_tests/lazy_torch_compile.py index b950877a4..b3b580952 100644 --- a/tests/standalone_tests/lazy_torch_compile.py +++ b/tests/standalone_tests/lazy_torch_compile.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Description: Test the lazy import module # The utility function cannot be placed in `vllm.utils` # this needs to be a standalone script diff --git a/tests/tensorizer_loader/conftest.py b/tests/tensorizer_loader/conftest.py index 2a4565362..694bb5fbc 100644 --- a/tests/tensorizer_loader/conftest.py +++ b/tests/tensorizer_loader/conftest.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import functools import gc from typing import Callable, TypeVar diff --git a/tests/tensorizer_loader/test_tensorizer.py b/tests/tensorizer_loader/test_tensorizer.py index 6e7eec1c6..b268d4bf0 100644 --- a/tests/tensorizer_loader/test_tensorizer.py +++ b/tests/tensorizer_loader/test_tensorizer.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import gc import json import os diff --git a/tests/test_cache_block_hashing.py b/tests/test_cache_block_hashing.py index e8f8499aa..17c128a17 100644 --- a/tests/test_cache_block_hashing.py +++ b/tests/test_cache_block_hashing.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Test hashing of cache blocks. Run `pytest tests/test_cache_block_hashing.py`. diff --git a/tests/test_config.py b/tests/test_config.py index ec366b93d..2dfae218b 100644 --- a/tests/test_config.py +++ b/tests/test_config.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from dataclasses import asdict import pytest diff --git a/tests/test_embedded_commit.py b/tests/test_embedded_commit.py index ffeacf34b..a9b4f5cbf 100644 --- a/tests/test_embedded_commit.py +++ b/tests/test_embedded_commit.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import vllm diff --git a/tests/test_inputs.py b/tests/test_inputs.py index fff7c5fc0..fff909154 100644 --- a/tests/test_inputs.py +++ b/tests/test_inputs.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List import pytest diff --git a/tests/test_logger.py b/tests/test_logger.py index e3749616d..993822e92 100644 --- a/tests/test_logger.py +++ b/tests/test_logger.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import json import logging import os diff --git a/tests/test_logits_processor.py b/tests/test_logits_processor.py index 39c1c3815..487fbb8fc 100644 --- a/tests/test_logits_processor.py +++ b/tests/test_logits_processor.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import random from typing import Tuple from unittest.mock import patch diff --git a/tests/test_regression.py b/tests/test_regression.py index 5d27d3579..f781b3113 100644 --- a/tests/test_regression.py +++ b/tests/test_regression.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Containing tests that check for regressions in vLLM's behavior. It should include tests that are reported by users and making sure they diff --git a/tests/test_sampling_params.py b/tests/test_sampling_params.py index 01cbe0c99..40e26ed51 100644 --- a/tests/test_sampling_params.py +++ b/tests/test_sampling_params.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Tests for the SamplingParams class. """ from vllm import SamplingParams diff --git a/tests/test_scalartype.py b/tests/test_scalartype.py index a9221f08c..6e36f2c33 100644 --- a/tests/test_scalartype.py +++ b/tests/test_scalartype.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import pytest import torch diff --git a/tests/test_sequence.py b/tests/test_sequence.py index 30e53a180..902de1099 100644 --- a/tests/test_sequence.py +++ b/tests/test_sequence.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import pytest from vllm.model_executor.layers.sampler import SamplerOutput diff --git a/tests/test_sharded_state_loader.py b/tests/test_sharded_state_loader.py index 2412da503..088b95be7 100644 --- a/tests/test_sharded_state_loader.py +++ b/tests/test_sharded_state_loader.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import multiprocessing as mp import os import shutil diff --git a/tests/test_utils.py b/tests/test_utils.py index d5dc4464e..5b69ffd18 100644 --- a/tests/test_utils.py +++ b/tests/test_utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import asyncio import os import socket diff --git a/tests/tokenization/test_cached_tokenizer.py b/tests/tokenization/test_cached_tokenizer.py index 4c8238fd8..cd60cefd7 100644 --- a/tests/tokenization/test_cached_tokenizer.py +++ b/tests/tokenization/test_cached_tokenizer.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from copy import deepcopy from transformers import AutoTokenizer diff --git a/tests/tokenization/test_detokenize.py b/tests/tokenization/test_detokenize.py index 84348cbc0..57832394d 100644 --- a/tests/tokenization/test_detokenize.py +++ b/tests/tokenization/test_detokenize.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Any, Dict, Generator, List, Optional import pytest diff --git a/tests/tokenization/test_get_eos.py b/tests/tokenization/test_get_eos.py index 875ca19d3..787fb6ea6 100644 --- a/tests/tokenization/test_get_eos.py +++ b/tests/tokenization/test_get_eos.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """ This test file includes some cases where it is inappropriate to only get the `eos_token_id` from the tokenizer as defined by diff --git a/tests/tokenization/test_tokenizer.py b/tests/tokenization/test_tokenizer.py index 8db7204f1..eddc63098 100644 --- a/tests/tokenization/test_tokenizer.py +++ b/tests/tokenization/test_tokenizer.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import pytest from transformers import PreTrainedTokenizerBase diff --git a/tests/tokenization/test_tokenizer_group.py b/tests/tokenization/test_tokenizer_group.py index 3faaf326f..8e99f8691 100644 --- a/tests/tokenization/test_tokenizer_group.py +++ b/tests/tokenization/test_tokenizer_group.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import asyncio import os import sys diff --git a/tests/tool_use/conftest.py b/tests/tool_use/conftest.py index 294acf202..39ab01c9b 100644 --- a/tests/tool_use/conftest.py +++ b/tests/tool_use/conftest.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import pytest import pytest_asyncio from huggingface_hub import snapshot_download diff --git a/tests/tool_use/test_chat_completion_request_validations.py b/tests/tool_use/test_chat_completion_request_validations.py index 3d0fe8f06..7bee56281 100644 --- a/tests/tool_use/test_chat_completion_request_validations.py +++ b/tests/tool_use/test_chat_completion_request_validations.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import pytest from vllm.entrypoints.openai.protocol import ChatCompletionRequest diff --git a/tests/tool_use/test_chat_completions.py b/tests/tool_use/test_chat_completions.py index 75bbfbb76..da033fa1d 100644 --- a/tests/tool_use/test_chat_completions.py +++ b/tests/tool_use/test_chat_completions.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List import openai diff --git a/tests/tool_use/test_jamba_tool_parser.py b/tests/tool_use/test_jamba_tool_parser.py index 3095ef451..7e349c512 100644 --- a/tests/tool_use/test_jamba_tool_parser.py +++ b/tests/tool_use/test_jamba_tool_parser.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import json from typing import Generator, List, Optional diff --git a/tests/tool_use/test_parallel_tool_calls.py b/tests/tool_use/test_parallel_tool_calls.py index c294cb049..b49a5e8e7 100644 --- a/tests/tool_use/test_parallel_tool_calls.py +++ b/tests/tool_use/test_parallel_tool_calls.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import json from typing import Dict, List, Optional diff --git a/tests/tool_use/test_tool_calls.py b/tests/tool_use/test_tool_calls.py index fe8cb496c..45f1bfc45 100644 --- a/tests/tool_use/test_tool_calls.py +++ b/tests/tool_use/test_tool_calls.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import json from typing import Dict, List, Optional diff --git a/tests/tool_use/utils.py b/tests/tool_use/utils.py index 2241f1846..a7dfb1078 100644 --- a/tests/tool_use/utils.py +++ b/tests/tool_use/utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from copy import deepcopy from typing import Any, Dict, List, Optional diff --git a/tests/tpu/test_compilation.py b/tests/tpu/test_compilation.py index b7124ebc1..6ed83f30e 100644 --- a/tests/tpu/test_compilation.py +++ b/tests/tpu/test_compilation.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import glob import os import tempfile diff --git a/tests/tpu/test_custom_dispatcher.py b/tests/tpu/test_custom_dispatcher.py index bb1379deb..e94bbd287 100644 --- a/tests/tpu/test_custom_dispatcher.py +++ b/tests/tpu/test_custom_dispatcher.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import os from vllm.config import CompilationLevel diff --git a/tests/tpu/test_quantization_accuracy.py b/tests/tpu/test_quantization_accuracy.py index 6cd5615c4..3db9bc73a 100644 --- a/tests/tpu/test_quantization_accuracy.py +++ b/tests/tpu/test_quantization_accuracy.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from dataclasses import dataclass import lm_eval diff --git a/tests/tracing/test_tracing.py b/tests/tracing/test_tracing.py index 49a16d16e..592775e8b 100644 --- a/tests/tracing/test_tracing.py +++ b/tests/tracing/test_tracing.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import os import threading from concurrent import futures diff --git a/tests/utils.py b/tests/utils.py index f4eecf19e..3b32052fe 100644 --- a/tests/utils.py +++ b/tests/utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import asyncio import copy import functools diff --git a/tests/v1/core/test_kv_cache_utils.py b/tests/v1/core/test_kv_cache_utils.py index 0a5ba1f98..60cf4384d 100644 --- a/tests/v1/core/test_kv_cache_utils.py +++ b/tests/v1/core/test_kv_cache_utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import pytest from vllm.multimodal.inputs import MultiModalKwargs diff --git a/tests/v1/core/test_prefix_caching.py b/tests/v1/core/test_prefix_caching.py index 5c1cda285..2e16d7d25 100644 --- a/tests/v1/core/test_prefix_caching.py +++ b/tests/v1/core/test_prefix_caching.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Compare the with and without prefix caching.""" import pytest diff --git a/tests/v1/e2e/test_cascade_attention.py b/tests/v1/e2e/test_cascade_attention.py index 8ec9f1ba3..a8079dcce 100644 --- a/tests/v1/e2e/test_cascade_attention.py +++ b/tests/v1/e2e/test_cascade_attention.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from vllm import LLM, SamplingParams diff --git a/tests/v1/engine/test_async_llm.py b/tests/v1/engine/test_async_llm.py index 10f783b21..4b5bc9ced 100644 --- a/tests/v1/engine/test_async_llm.py +++ b/tests/v1/engine/test_async_llm.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import asyncio from contextlib import ExitStack from typing import List, Tuple diff --git a/tests/v1/engine/test_engine_args.py b/tests/v1/engine/test_engine_args.py index ff38a4568..a3540582a 100644 --- a/tests/v1/engine/test_engine_args.py +++ b/tests/v1/engine/test_engine_args.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import pytest from vllm import envs diff --git a/tests/v1/engine/test_engine_core.py b/tests/v1/engine/test_engine_core.py index 033bbcfce..6a91f1901 100644 --- a/tests/v1/engine/test_engine_core.py +++ b/tests/v1/engine/test_engine_core.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import time import uuid diff --git a/tests/v1/engine/test_engine_core_client.py b/tests/v1/engine/test_engine_core_client.py index e2c728b22..b2539132f 100644 --- a/tests/v1/engine/test_engine_core_client.py +++ b/tests/v1/engine/test_engine_core_client.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import asyncio import time import uuid diff --git a/tests/v1/engine/test_output_processor.py b/tests/v1/engine/test_output_processor.py index 4735c6f94..5782a249f 100644 --- a/tests/v1/engine/test_output_processor.py +++ b/tests/v1/engine/test_output_processor.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List import pytest diff --git a/tests/v1/sample/test_sampler.py b/tests/v1/sample/test_sampler.py index 5ebf72927..f7eedcb9c 100644 --- a/tests/v1/sample/test_sampler.py +++ b/tests/v1/sample/test_sampler.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List, Set, Tuple import numpy as np diff --git a/tests/v1/test_stats.py b/tests/v1/test_stats.py index 580392ac5..48419d8a2 100644 --- a/tests/v1/test_stats.py +++ b/tests/v1/test_stats.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import pytest from vllm.sampling_params import SamplingParams diff --git a/tests/v1/test_utils.py b/tests/v1/test_utils.py index ac773b611..9b669ae00 100644 --- a/tests/v1/test_utils.py +++ b/tests/v1/test_utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List import torch diff --git a/tests/v1/worker/test_gpu_input_batch.py b/tests/v1/worker/test_gpu_input_batch.py index 694ce81ff..5b40fbff8 100644 --- a/tests/v1/worker/test_gpu_input_batch.py +++ b/tests/v1/worker/test_gpu_input_batch.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Dict, List, Set, Tuple import numpy as np diff --git a/tests/vllm_test_utils/setup.py b/tests/vllm_test_utils/setup.py index 790e891ec..c03943149 100644 --- a/tests/vllm_test_utils/setup.py +++ b/tests/vllm_test_utils/setup.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from setuptools import setup setup( diff --git a/tests/vllm_test_utils/vllm_test_utils/__init__.py b/tests/vllm_test_utils/vllm_test_utils/__init__.py index 6505c8154..1d1219fbe 100644 --- a/tests/vllm_test_utils/vllm_test_utils/__init__.py +++ b/tests/vllm_test_utils/vllm_test_utils/__init__.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """ vllm_utils is a package for vLLM testing utilities. It does not import any vLLM modules. diff --git a/tests/vllm_test_utils/vllm_test_utils/blame.py b/tests/vllm_test_utils/vllm_test_utils/blame.py index 1ddd3471d..392fd2705 100644 --- a/tests/vllm_test_utils/vllm_test_utils/blame.py +++ b/tests/vllm_test_utils/vllm_test_utils/blame.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import contextlib import dataclasses import sys diff --git a/tests/vllm_test_utils/vllm_test_utils/monitor.py b/tests/vllm_test_utils/vllm_test_utils/monitor.py index a237f53a7..44d45f262 100644 --- a/tests/vllm_test_utils/vllm_test_utils/monitor.py +++ b/tests/vllm_test_utils/vllm_test_utils/monitor.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import contextlib import dataclasses import sys diff --git a/tests/weight_loading/test_weight_loading.py b/tests/weight_loading/test_weight_loading.py index 7a3786456..e456bfab8 100644 --- a/tests/weight_loading/test_weight_loading.py +++ b/tests/weight_loading/test_weight_loading.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import os import pytest diff --git a/tests/worker/test_encoder_decoder_model_runner.py b/tests/worker/test_encoder_decoder_model_runner.py index a6b3cb575..0ce0465a7 100644 --- a/tests/worker/test_encoder_decoder_model_runner.py +++ b/tests/worker/test_encoder_decoder_model_runner.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import itertools from typing import List diff --git a/tests/worker/test_model_input.py b/tests/worker/test_model_input.py index 57f1fd47a..eb341fb1b 100644 --- a/tests/worker/test_model_input.py +++ b/tests/worker/test_model_input.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import dataclasses from typing import List, Tuple, Type diff --git a/tests/worker/test_model_runner.py b/tests/worker/test_model_runner.py index aabe913c2..c32ceb4fa 100644 --- a/tests/worker/test_model_runner.py +++ b/tests/worker/test_model_runner.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List import pytest diff --git a/tests/worker/test_profile.py b/tests/worker/test_profile.py index 79233c757..22466105b 100644 --- a/tests/worker/test_profile.py +++ b/tests/worker/test_profile.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import torch from vllm.engine.arg_utils import EngineArgs diff --git a/tests/worker/test_swap.py b/tests/worker/test_swap.py index acede959f..7ae0f4bb8 100644 --- a/tests/worker/test_swap.py +++ b/tests/worker/test_swap.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import torch from vllm.engine.arg_utils import EngineArgs diff --git a/tools/check_spdx_header.py b/tools/check_spdx_header.py new file mode 100644 index 000000000..3f7fd66bf --- /dev/null +++ b/tools/check_spdx_header.py @@ -0,0 +1,43 @@ +# SPDX-License-Identifier: Apache-2.0 + +import sys + +SPDX_HEADER = "# SPDX-License-Identifier: Apache-2.0" +SPDX_HEADER_PREFIX = "# SPDX-License-Identifier:" + + +def check_spdx_header(file_path): + with open(file_path, encoding='UTF-8') as file: + lines = file.readlines() + if not lines: + # not necessary for an empty file like __init__.py + return True + if not lines[0].strip().startswith(SPDX_HEADER_PREFIX): + return False + return True + + +def add_header(file_path): + with open(file_path, 'r+', encoding='UTF-8') as file: + lines = file.readlines() + file.seek(0, 0) + file.write(SPDX_HEADER + '\n\n' + ''.join(lines)) + + +def main(): + files_with_missing_header = [] + for file_path in sys.argv[1:]: + if not check_spdx_header(file_path): + files_with_missing_header.append(file_path) + + if files_with_missing_header: + print("The following files are missing the SPDX header:") + for file_path in files_with_missing_header: + print(f" {file_path}") + add_header(file_path) + + sys.exit(1 if files_with_missing_header else 0) + + +if __name__ == "__main__": + main() diff --git a/tools/profiler/print_layerwise_table.py b/tools/profiler/print_layerwise_table.py index 54cd60c2b..adbb7301b 100644 --- a/tools/profiler/print_layerwise_table.py +++ b/tools/profiler/print_layerwise_table.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import argparse import json from typing import Dict diff --git a/tools/profiler/visualize_layerwise_profile.py b/tools/profiler/visualize_layerwise_profile.py index cb56ebd69..c527cdbe0 100644 --- a/tools/profiler/visualize_layerwise_profile.py +++ b/tools/profiler/visualize_layerwise_profile.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import argparse import copy import json diff --git a/tools/report_build_time_ninja.py b/tools/report_build_time_ninja.py index 9dc19f5fd..33e85b9ff 100644 --- a/tools/report_build_time_ninja.py +++ b/tools/report_build_time_ninja.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + #!/usr/bin/env python3 # Copyright (c) 2018 The Chromium Authors. All rights reserved. # Use of this source code is governed by a BSD-style license that can be diff --git a/use_existing_torch.py b/use_existing_torch.py index 319d26289..a578328b0 100644 --- a/use_existing_torch.py +++ b/use_existing_torch.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import glob requires_files = glob.glob('requirements*.txt') diff --git a/vllm/__init__.py b/vllm/__init__.py index 2aabe820d..566c5116d 100644 --- a/vllm/__init__.py +++ b/vllm/__init__.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """vLLM: a high-throughput and memory-efficient inference engine for LLMs""" import os diff --git a/vllm/_custom_ops.py b/vllm/_custom_ops.py index da237da2e..ce4f75341 100644 --- a/vllm/_custom_ops.py +++ b/vllm/_custom_ops.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import contextlib import importlib from typing import TYPE_CHECKING, List, Optional, Tuple, Union diff --git a/vllm/_ipex_ops.py b/vllm/_ipex_ops.py index 28b804f76..ccb67baa5 100644 --- a/vllm/_ipex_ops.py +++ b/vllm/_ipex_ops.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List, Optional, Tuple import torch diff --git a/vllm/adapter_commons/layers.py b/vllm/adapter_commons/layers.py index 3ed60678b..18e0c5227 100644 --- a/vllm/adapter_commons/layers.py +++ b/vllm/adapter_commons/layers.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from dataclasses import dataclass from typing import Tuple diff --git a/vllm/adapter_commons/models.py b/vllm/adapter_commons/models.py index 468904c90..f9a5d2fff 100644 --- a/vllm/adapter_commons/models.py +++ b/vllm/adapter_commons/models.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from abc import ABC, abstractmethod from typing import Any, Callable, Dict, Optional, TypeVar diff --git a/vllm/adapter_commons/request.py b/vllm/adapter_commons/request.py index 2bb17fdc0..2b604b91b 100644 --- a/vllm/adapter_commons/request.py +++ b/vllm/adapter_commons/request.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from abc import ABC, abstractmethod diff --git a/vllm/adapter_commons/utils.py b/vllm/adapter_commons/utils.py index 1e9adca50..c2dc5433c 100644 --- a/vllm/adapter_commons/utils.py +++ b/vllm/adapter_commons/utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Any, Callable, Dict, Optional, Set diff --git a/vllm/adapter_commons/worker_manager.py b/vllm/adapter_commons/worker_manager.py index 83929e82e..ce24e08a5 100644 --- a/vllm/adapter_commons/worker_manager.py +++ b/vllm/adapter_commons/worker_manager.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from abc import ABC, abstractmethod from typing import Any, Optional, Set diff --git a/vllm/assets/audio.py b/vllm/assets/audio.py index a46c67ad7..d9e51082e 100644 --- a/vllm/assets/audio.py +++ b/vllm/assets/audio.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from dataclasses import dataclass from typing import Literal from urllib.parse import urljoin diff --git a/vllm/assets/base.py b/vllm/assets/base.py index 249173141..03f3b9dab 100644 --- a/vllm/assets/base.py +++ b/vllm/assets/base.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from functools import lru_cache from pathlib import Path from typing import Optional diff --git a/vllm/assets/image.py b/vllm/assets/image.py index 0a55506f8..2b1d258da 100644 --- a/vllm/assets/image.py +++ b/vllm/assets/image.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from dataclasses import dataclass from typing import Literal diff --git a/vllm/assets/video.py b/vllm/assets/video.py index eca2ccc54..494cfc383 100644 --- a/vllm/assets/video.py +++ b/vllm/assets/video.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from dataclasses import dataclass from functools import lru_cache from typing import List, Literal diff --git a/vllm/attention/__init__.py b/vllm/attention/__init__.py index 2cd4ad3e0..85c5715fa 100644 --- a/vllm/attention/__init__.py +++ b/vllm/attention/__init__.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from vllm.attention.backends.abstract import (AttentionBackend, AttentionMetadata, AttentionMetadataBuilder, diff --git a/vllm/attention/backends/abstract.py b/vllm/attention/backends/abstract.py index b9425f659..5f0a54013 100644 --- a/vllm/attention/backends/abstract.py +++ b/vllm/attention/backends/abstract.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from abc import ABC, abstractmethod from contextlib import contextmanager from dataclasses import dataclass, fields diff --git a/vllm/attention/backends/blocksparse_attn.py b/vllm/attention/backends/blocksparse_attn.py index 20e9a3f13..9765e7881 100644 --- a/vllm/attention/backends/blocksparse_attn.py +++ b/vllm/attention/backends/blocksparse_attn.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from dataclasses import dataclass, field from typing import Any, Dict, List, Optional, Tuple, Type diff --git a/vllm/attention/backends/flash_attn.py b/vllm/attention/backends/flash_attn.py index 4a9aa1e21..6a82127ac 100755 --- a/vllm/attention/backends/flash_attn.py +++ b/vllm/attention/backends/flash_attn.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Attention layer with FlashAttention.""" from collections import defaultdict from dataclasses import dataclass diff --git a/vllm/attention/backends/flashinfer.py b/vllm/attention/backends/flashinfer.py index 7cccef960..715ed6748 100644 --- a/vllm/attention/backends/flashinfer.py +++ b/vllm/attention/backends/flashinfer.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import dataclasses from collections import defaultdict from contextlib import contextmanager diff --git a/vllm/attention/backends/hpu_attn.py b/vllm/attention/backends/hpu_attn.py index 80c132c0a..1518e518e 100644 --- a/vllm/attention/backends/hpu_attn.py +++ b/vllm/attention/backends/hpu_attn.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + ############################################################################### # Copyright (C) 2024 Habana Labs, Ltd. an Intel Company ############################################################################### diff --git a/vllm/attention/backends/ipex_attn.py b/vllm/attention/backends/ipex_attn.py index 57916a3c6..b4879af4c 100644 --- a/vllm/attention/backends/ipex_attn.py +++ b/vllm/attention/backends/ipex_attn.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """ Attention layer with torch scaled_dot_product_attention and PagedAttention.""" from dataclasses import dataclass diff --git a/vllm/attention/backends/mla/utils.py b/vllm/attention/backends/mla/utils.py index e8fec234c..9b63192ed 100644 --- a/vllm/attention/backends/mla/utils.py +++ b/vllm/attention/backends/mla/utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from abc import abstractmethod from dataclasses import dataclass from typing import Any, Dict, Generic, List, Optional, Tuple diff --git a/vllm/attention/backends/openvino.py b/vllm/attention/backends/openvino.py index be06d1600..f58528dbf 100644 --- a/vllm/attention/backends/openvino.py +++ b/vllm/attention/backends/openvino.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from dataclasses import dataclass from typing import Dict, List, Optional, Tuple, Type diff --git a/vllm/attention/backends/pallas.py b/vllm/attention/backends/pallas.py index 209a623ba..b61dfe63d 100644 --- a/vllm/attention/backends/pallas.py +++ b/vllm/attention/backends/pallas.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from dataclasses import dataclass from typing import Any, Dict, List, Optional, Tuple, Type diff --git a/vllm/attention/backends/placeholder_attn.py b/vllm/attention/backends/placeholder_attn.py index 826311896..9f6e731af 100644 --- a/vllm/attention/backends/placeholder_attn.py +++ b/vllm/attention/backends/placeholder_attn.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from collections import defaultdict from dataclasses import dataclass from typing import TYPE_CHECKING, Dict, List, Optional, Tuple, Type diff --git a/vllm/attention/backends/rocm_flash_attn.py b/vllm/attention/backends/rocm_flash_attn.py index 12110ec73..02bff57a6 100644 --- a/vllm/attention/backends/rocm_flash_attn.py +++ b/vllm/attention/backends/rocm_flash_attn.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Attention layer ROCm GPUs.""" from dataclasses import dataclass from typing import TYPE_CHECKING, Any, Dict, List, Optional, Tuple, Type diff --git a/vllm/attention/backends/torch_sdpa.py b/vllm/attention/backends/torch_sdpa.py index c3b2398b4..25fe6ed95 100644 --- a/vllm/attention/backends/torch_sdpa.py +++ b/vllm/attention/backends/torch_sdpa.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """ Attention layer with torch scaled_dot_product_attention and PagedAttention.""" from dataclasses import dataclass diff --git a/vllm/attention/backends/triton_mla.py b/vllm/attention/backends/triton_mla.py index 95dc119a4..20d7ef0fa 100644 --- a/vllm/attention/backends/triton_mla.py +++ b/vllm/attention/backends/triton_mla.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from collections import defaultdict from contextlib import contextmanager from dataclasses import dataclass diff --git a/vllm/attention/backends/utils.py b/vllm/attention/backends/utils.py index 7f2fe7e83..ad53e4e70 100644 --- a/vllm/attention/backends/utils.py +++ b/vllm/attention/backends/utils.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Attention backend utils""" from collections import defaultdict from contextlib import contextmanager diff --git a/vllm/attention/backends/xformers.py b/vllm/attention/backends/xformers.py index 49f47f9c8..723a4558d 100644 --- a/vllm/attention/backends/xformers.py +++ b/vllm/attention/backends/xformers.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Attention layer with xFormers and PagedAttention.""" from dataclasses import dataclass from typing import Any, Dict, List, Optional, Tuple, Type diff --git a/vllm/attention/layer.py b/vllm/attention/layer.py index b97165f62..19ee89630 100644 --- a/vllm/attention/layer.py +++ b/vllm/attention/layer.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Attention layer.""" from typing import Any, Dict, List, Optional diff --git a/vllm/attention/ops/blocksparse_attention/blocksparse_attention_kernel.py b/vllm/attention/ops/blocksparse_attention/blocksparse_attention_kernel.py index 727a470ba..71caf3cba 100644 --- a/vllm/attention/ops/blocksparse_attention/blocksparse_attention_kernel.py +++ b/vllm/attention/ops/blocksparse_attention/blocksparse_attention_kernel.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import torch import triton import triton.language as tl diff --git a/vllm/attention/ops/blocksparse_attention/interface.py b/vllm/attention/ops/blocksparse_attention/interface.py index 350f88c8f..6ab69ea5b 100644 --- a/vllm/attention/ops/blocksparse_attention/interface.py +++ b/vllm/attention/ops/blocksparse_attention/interface.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import math import torch diff --git a/vllm/attention/ops/blocksparse_attention/utils.py b/vllm/attention/ops/blocksparse_attention/utils.py index 78d752230..4de9bd530 100644 --- a/vllm/attention/ops/blocksparse_attention/utils.py +++ b/vllm/attention/ops/blocksparse_attention/utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Helper functions for 3D sparse pattern # These function are not optimized and very inefficient. # Avoid calling them too frequent or use a cache mechanism. diff --git a/vllm/attention/ops/hpu_paged_attn.py b/vllm/attention/ops/hpu_paged_attn.py index 4c0fb2a62..8bb536343 100644 --- a/vllm/attention/ops/hpu_paged_attn.py +++ b/vllm/attention/ops/hpu_paged_attn.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + ############################################################################### # Copyright (C) 2024 Habana Labs, Ltd. an Intel Company ############################################################################### diff --git a/vllm/attention/ops/ipex_attn.py b/vllm/attention/ops/ipex_attn.py index 3a07184ed..598ceea13 100644 --- a/vllm/attention/ops/ipex_attn.py +++ b/vllm/attention/ops/ipex_attn.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Dict, List, Optional, Tuple try: diff --git a/vllm/attention/ops/nki_flash_attn.py b/vllm/attention/ops/nki_flash_attn.py index 9de4ef7f5..68aa63f5a 100644 --- a/vllm/attention/ops/nki_flash_attn.py +++ b/vllm/attention/ops/nki_flash_attn.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from dataclasses import dataclass import neuronxcc.nki.isa as nisa diff --git a/vllm/attention/ops/paged_attn.py b/vllm/attention/ops/paged_attn.py index fd6232914..2c60bd0c3 100644 --- a/vllm/attention/ops/paged_attn.py +++ b/vllm/attention/ops/paged_attn.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from dataclasses import dataclass from typing import List, Optional, Tuple diff --git a/vllm/attention/ops/prefix_prefill.py b/vllm/attention/ops/prefix_prefill.py index ec3c8459c..fbb6757ee 100644 --- a/vllm/attention/ops/prefix_prefill.py +++ b/vllm/attention/ops/prefix_prefill.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # The kernels in this file are adapted from LightLLM's context_attention_fwd: # https://github.com/ModelTC/lightllm/blob/main/lightllm/models/llama/triton_kernel/context_flashattention_nopad.py diff --git a/vllm/attention/ops/triton_decode_attention.py b/vllm/attention/ops/triton_decode_attention.py index 675df109b..ec5ec4ce6 100644 --- a/vllm/attention/ops/triton_decode_attention.py +++ b/vllm/attention/ops/triton_decode_attention.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Adapted from # https://github.com/sgl-project/sglang/blob/9f635ea50de920aa507f486daafba26a5b837574/python/sglang/srt/layers/attention/triton_ops/decode_attention.py # which was originally adapted from diff --git a/vllm/attention/ops/triton_flash_attention.py b/vllm/attention/ops/triton_flash_attention.py index ef04603f2..ab8fb8953 100644 --- a/vllm/attention/ops/triton_flash_attention.py +++ b/vllm/attention/ops/triton_flash_attention.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + #!/usr/bin/env python """ Fused Attention diff --git a/vllm/attention/selector.py b/vllm/attention/selector.py index 4c6bbc727..26c6ac812 100644 --- a/vllm/attention/selector.py +++ b/vllm/attention/selector.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import os from contextlib import contextmanager from functools import cache diff --git a/vllm/beam_search.py b/vllm/beam_search.py index 026037e54..97b2b630f 100644 --- a/vllm/beam_search.py +++ b/vllm/beam_search.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from dataclasses import dataclass from typing import TYPE_CHECKING, Any, Dict, List, Optional, Union diff --git a/vllm/compilation/backends.py b/vllm/compilation/backends.py index 7f4f97466..979890170 100644 --- a/vllm/compilation/backends.py +++ b/vllm/compilation/backends.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import ast import copy import dataclasses diff --git a/vllm/compilation/counter.py b/vllm/compilation/counter.py index 6385f1c5d..a6f11a3af 100644 --- a/vllm/compilation/counter.py +++ b/vllm/compilation/counter.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import copy import dataclasses from contextlib import contextmanager diff --git a/vllm/compilation/decorators.py b/vllm/compilation/decorators.py index 17eb0592c..20afe6967 100644 --- a/vllm/compilation/decorators.py +++ b/vllm/compilation/decorators.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import inspect from typing import Callable, Dict, List, Optional, TypeVar, Union, overload from unittest.mock import patch diff --git a/vllm/compilation/fix_functionalization.py b/vllm/compilation/fix_functionalization.py index e15d7b315..9b0e9c5d0 100644 --- a/vllm/compilation/fix_functionalization.py +++ b/vllm/compilation/fix_functionalization.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import operator from typing import Dict, Iterable, List, Optional, Tuple, Union diff --git a/vllm/compilation/fusion.py b/vllm/compilation/fusion.py index cde27bd10..0c3d8697b 100644 --- a/vllm/compilation/fusion.py +++ b/vllm/compilation/fusion.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Callable, Dict, List, NamedTuple, Optional, Tuple import torch diff --git a/vllm/compilation/fx_utils.py b/vllm/compilation/fx_utils.py index 924e26f2e..b9a8d3112 100644 --- a/vllm/compilation/fx_utils.py +++ b/vllm/compilation/fx_utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import operator from typing import Iterable, Optional diff --git a/vllm/compilation/inductor_pass.py b/vllm/compilation/inductor_pass.py index f6846c08a..be663946f 100644 --- a/vllm/compilation/inductor_pass.py +++ b/vllm/compilation/inductor_pass.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import hashlib import inspect import types diff --git a/vllm/compilation/monitor.py b/vllm/compilation/monitor.py index b97e40415..786c7c1e1 100644 --- a/vllm/compilation/monitor.py +++ b/vllm/compilation/monitor.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import os import time diff --git a/vllm/compilation/multi_output_match.py b/vllm/compilation/multi_output_match.py index b6bcecdc8..e6f6a60b2 100644 --- a/vllm/compilation/multi_output_match.py +++ b/vllm/compilation/multi_output_match.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import abc import operator from abc import abstractmethod diff --git a/vllm/compilation/pass_manager.py b/vllm/compilation/pass_manager.py index 34f5f3557..c7387fb7c 100644 --- a/vllm/compilation/pass_manager.py +++ b/vllm/compilation/pass_manager.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Any, Dict, List from torch import fx as fx diff --git a/vllm/compilation/reshapes.py b/vllm/compilation/reshapes.py index ba28b1f0b..292baae85 100644 --- a/vllm/compilation/reshapes.py +++ b/vllm/compilation/reshapes.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Union import torch.fx diff --git a/vllm/compilation/vllm_inductor_pass.py b/vllm/compilation/vllm_inductor_pass.py index b8c52a7f4..1d2597e42 100644 --- a/vllm/compilation/vllm_inductor_pass.py +++ b/vllm/compilation/vllm_inductor_pass.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import time import torch diff --git a/vllm/compilation/wrapper.py b/vllm/compilation/wrapper.py index 58a8fa76f..a8a283ddd 100644 --- a/vllm/compilation/wrapper.py +++ b/vllm/compilation/wrapper.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import os import sys from abc import abstractmethod diff --git a/vllm/config.py b/vllm/config.py index a13700aba..d2d59c705 100644 --- a/vllm/config.py +++ b/vllm/config.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import ast import copy import enum diff --git a/vllm/connections.py b/vllm/connections.py index 4c9f4f40c..dc060bb6f 100644 --- a/vllm/connections.py +++ b/vllm/connections.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from pathlib import Path from typing import Mapping, MutableMapping, Optional from urllib.parse import urlparse diff --git a/vllm/core/block/block_table.py b/vllm/core/block/block_table.py index 90c1438ef..d4d31c58d 100644 --- a/vllm/core/block/block_table.py +++ b/vllm/core/block/block_table.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import math from typing import List, Optional diff --git a/vllm/core/block/common.py b/vllm/core/block/common.py index 115f663e4..1966eac1c 100644 --- a/vllm/core/block/common.py +++ b/vllm/core/block/common.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from collections import deque from dataclasses import dataclass from typing import Deque, Dict, Iterable, List, Optional, Protocol, Tuple diff --git a/vllm/core/block/cpu_gpu_block_allocator.py b/vllm/core/block/cpu_gpu_block_allocator.py index c3e1665b4..359b5b263 100644 --- a/vllm/core/block/cpu_gpu_block_allocator.py +++ b/vllm/core/block/cpu_gpu_block_allocator.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Dict, FrozenSet, List, Optional, Tuple from vllm.core.block.interfaces import (Block, BlockAllocator, BlockId, diff --git a/vllm/core/block/interfaces.py b/vllm/core/block/interfaces.py index cb432db91..0b0197deb 100644 --- a/vllm/core/block/interfaces.py +++ b/vllm/core/block/interfaces.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from abc import ABC, abstractmethod from typing import Dict, FrozenSet, List, Optional, Protocol, Tuple diff --git a/vllm/core/block/naive_block.py b/vllm/core/block/naive_block.py index c38ae2dd6..c388366b8 100644 --- a/vllm/core/block/naive_block.py +++ b/vllm/core/block/naive_block.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from collections import deque from typing import Deque, FrozenSet, Iterable, List, Optional, Tuple, Union diff --git a/vllm/core/block/prefix_caching_block.py b/vllm/core/block/prefix_caching_block.py index ccdc5daa9..fbf19e1b4 100644 --- a/vllm/core/block/prefix_caching_block.py +++ b/vllm/core/block/prefix_caching_block.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Token blocks.""" import sys from bisect import bisect_left diff --git a/vllm/core/block/utils.py b/vllm/core/block/utils.py index 1c6578e4c..910afdd9f 100644 --- a/vllm/core/block/utils.py +++ b/vllm/core/block/utils.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Block manager utils.""" from vllm.sequence import SequenceGroup from vllm.utils import (STR_NOT_IMPL_ENC_DEC_PREFIX_CACHE, diff --git a/vllm/core/block_manager.py b/vllm/core/block_manager.py index 2d6a132ed..c5b3b04f3 100644 --- a/vllm/core/block_manager.py +++ b/vllm/core/block_manager.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """A block manager that manages token blocks.""" from typing import Dict, List, Optional from typing import Sequence as GenericSequence diff --git a/vllm/core/evictor.py b/vllm/core/evictor.py index c93065182..0e363eddc 100644 --- a/vllm/core/evictor.py +++ b/vllm/core/evictor.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import enum import heapq from abc import ABC, abstractmethod diff --git a/vllm/core/interfaces.py b/vllm/core/interfaces.py index 9c7e246e3..b48ba87e9 100644 --- a/vllm/core/interfaces.py +++ b/vllm/core/interfaces.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import enum from abc import ABC, abstractmethod from typing import List diff --git a/vllm/core/placeholder_block_space_manager.py b/vllm/core/placeholder_block_space_manager.py index f9924be4a..70c22afa8 100644 --- a/vllm/core/placeholder_block_space_manager.py +++ b/vllm/core/placeholder_block_space_manager.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List, Tuple from vllm.core.interfaces import AllocStatus, BlockSpaceManager diff --git a/vllm/core/scheduler.py b/vllm/core/scheduler.py index 2bb961481..f507847ad 100644 --- a/vllm/core/scheduler.py +++ b/vllm/core/scheduler.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import enum import os import random diff --git a/vllm/device_allocator/cumem.py b/vllm/device_allocator/cumem.py index a43418dbb..f74ad9ac3 100644 --- a/vllm/device_allocator/cumem.py +++ b/vllm/device_allocator/cumem.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # cumem-based pytorch pluggable allocator to implement sleep mode. # other approaches tried but failed: # - cuda-python package binding diff --git a/vllm/distributed/__init__.py b/vllm/distributed/__init__.py index db325cfab..39955ddac 100644 --- a/vllm/distributed/__init__.py +++ b/vllm/distributed/__init__.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from .communication_op import * from .parallel_state import * from .utils import * diff --git a/vllm/distributed/communication_op.py b/vllm/distributed/communication_op.py index e13505dc3..0228264f9 100644 --- a/vllm/distributed/communication_op.py +++ b/vllm/distributed/communication_op.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Any, Dict, Optional, Union import torch diff --git a/vllm/distributed/device_communicators/cuda_wrapper.py b/vllm/distributed/device_communicators/cuda_wrapper.py index d5a53381c..010caf7eb 100644 --- a/vllm/distributed/device_communicators/cuda_wrapper.py +++ b/vllm/distributed/device_communicators/cuda_wrapper.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """This file is a pure Python wrapper for the cudart library. It avoids the need to compile a separate shared library, and is convenient for use when we just need to call a few functions. diff --git a/vllm/distributed/device_communicators/custom_all_reduce.py b/vllm/distributed/device_communicators/custom_all_reduce.py index 62929dc0f..a2614ed5d 100644 --- a/vllm/distributed/device_communicators/custom_all_reduce.py +++ b/vllm/distributed/device_communicators/custom_all_reduce.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import ctypes from contextlib import contextmanager from typing import List, Optional, Union diff --git a/vllm/distributed/device_communicators/custom_all_reduce_utils.py b/vllm/distributed/device_communicators/custom_all_reduce_utils.py index 1f78e10cc..d8d6eed2d 100644 --- a/vllm/distributed/device_communicators/custom_all_reduce_utils.py +++ b/vllm/distributed/device_communicators/custom_all_reduce_utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import ctypes import json import os diff --git a/vllm/distributed/device_communicators/hpu_communicator.py b/vllm/distributed/device_communicators/hpu_communicator.py index cc9b19ce0..3f85da98a 100644 --- a/vllm/distributed/device_communicators/hpu_communicator.py +++ b/vllm/distributed/device_communicators/hpu_communicator.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import torch import torch.distributed as dist from torch.distributed import ProcessGroup diff --git a/vllm/distributed/device_communicators/pynccl.py b/vllm/distributed/device_communicators/pynccl.py index efc599871..0ccd42312 100644 --- a/vllm/distributed/device_communicators/pynccl.py +++ b/vllm/distributed/device_communicators/pynccl.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Optional, Union # ===================== import region ===================== diff --git a/vllm/distributed/device_communicators/pynccl_wrapper.py b/vllm/distributed/device_communicators/pynccl_wrapper.py index 7dea61b6a..03c3b0be7 100644 --- a/vllm/distributed/device_communicators/pynccl_wrapper.py +++ b/vllm/distributed/device_communicators/pynccl_wrapper.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # This file is a pure Python wrapper for the NCCL library. # The main purpose is to use NCCL combined with CUDA graph. # Before writing this script, we tried the following approach: diff --git a/vllm/distributed/device_communicators/shm_broadcast.py b/vllm/distributed/device_communicators/shm_broadcast.py index 268edc092..48ac81ac0 100644 --- a/vllm/distributed/device_communicators/shm_broadcast.py +++ b/vllm/distributed/device_communicators/shm_broadcast.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import os import pickle import sys diff --git a/vllm/distributed/device_communicators/tpu_communicator.py b/vllm/distributed/device_communicators/tpu_communicator.py index 765a0f9cb..7af7c65f6 100644 --- a/vllm/distributed/device_communicators/tpu_communicator.py +++ b/vllm/distributed/device_communicators/tpu_communicator.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import os import torch diff --git a/vllm/distributed/device_communicators/xpu_communicator.py b/vllm/distributed/device_communicators/xpu_communicator.py index eafd3c2f6..79ccc101e 100644 --- a/vllm/distributed/device_communicators/xpu_communicator.py +++ b/vllm/distributed/device_communicators/xpu_communicator.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import torch import torch.distributed as dist from torch.distributed import ProcessGroup diff --git a/vllm/distributed/kv_transfer/kv_connector/base.py b/vllm/distributed/kv_transfer/kv_connector/base.py index 6089e3bab..57c764b48 100644 --- a/vllm/distributed/kv_transfer/kv_connector/base.py +++ b/vllm/distributed/kv_transfer/kv_connector/base.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """ KVConnectorBase Class for Distributed KV Cache & Hidden State communication diff --git a/vllm/distributed/kv_transfer/kv_connector/factory.py b/vllm/distributed/kv_transfer/kv_connector/factory.py index 6372dab72..fe4805334 100644 --- a/vllm/distributed/kv_transfer/kv_connector/factory.py +++ b/vllm/distributed/kv_transfer/kv_connector/factory.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import importlib from typing import TYPE_CHECKING, Callable, Dict, Type diff --git a/vllm/distributed/kv_transfer/kv_connector/simple_connector.py b/vllm/distributed/kv_transfer/kv_connector/simple_connector.py index 7780e2dfa..2033e9762 100644 --- a/vllm/distributed/kv_transfer/kv_connector/simple_connector.py +++ b/vllm/distributed/kv_transfer/kv_connector/simple_connector.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """ Simple KV Cache Connector for Distributed Machine Learning Inference diff --git a/vllm/distributed/kv_transfer/kv_lookup_buffer/base.py b/vllm/distributed/kv_transfer/kv_lookup_buffer/base.py index bad119a1a..845da7c50 100644 --- a/vllm/distributed/kv_transfer/kv_lookup_buffer/base.py +++ b/vllm/distributed/kv_transfer/kv_lookup_buffer/base.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """ This file contains a new class `KVLookupBufferBase` that allows developers to think of KV cache operations as inserting new KV cache entries (`insert`) diff --git a/vllm/distributed/kv_transfer/kv_lookup_buffer/simple_buffer.py b/vllm/distributed/kv_transfer/kv_lookup_buffer/simple_buffer.py index fe8d8d737..5e1b62352 100644 --- a/vllm/distributed/kv_transfer/kv_lookup_buffer/simple_buffer.py +++ b/vllm/distributed/kv_transfer/kv_lookup_buffer/simple_buffer.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """ Implements a distributed key-value (KV) cache transfer mechanism. diff --git a/vllm/distributed/kv_transfer/kv_pipe/base.py b/vllm/distributed/kv_transfer/kv_pipe/base.py index 4b0cb44cc..40589fb3e 100644 --- a/vllm/distributed/kv_transfer/kv_pipe/base.py +++ b/vllm/distributed/kv_transfer/kv_pipe/base.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """ This file defines an interface `KVPipeBase` that provides an abstraction for sending and receiving tensors, or None, via diff --git a/vllm/distributed/kv_transfer/kv_pipe/mooncake_pipe.py b/vllm/distributed/kv_transfer/kv_pipe/mooncake_pipe.py index 8e4358672..58ab7f0b6 100644 --- a/vllm/distributed/kv_transfer/kv_pipe/mooncake_pipe.py +++ b/vllm/distributed/kv_transfer/kv_pipe/mooncake_pipe.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import json import os import pickle diff --git a/vllm/distributed/kv_transfer/kv_pipe/pynccl_pipe.py b/vllm/distributed/kv_transfer/kv_pipe/pynccl_pipe.py index 98222fa67..7aa53d07a 100644 --- a/vllm/distributed/kv_transfer/kv_pipe/pynccl_pipe.py +++ b/vllm/distributed/kv_transfer/kv_pipe/pynccl_pipe.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """ This module implements a PyNccl pipe for sending and receiving Optional[torch.Tensor] between distributed ranks with advanced diff --git a/vllm/distributed/kv_transfer/kv_transfer_agent.py b/vllm/distributed/kv_transfer/kv_transfer_agent.py index 9ce97851d..1e80e0bd7 100644 --- a/vllm/distributed/kv_transfer/kv_transfer_agent.py +++ b/vllm/distributed/kv_transfer/kv_transfer_agent.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """A centralized entrypoint to perform distributed KV cache transfer. This implementation is a shim wrapper on two APIs exposed by `kv_connector`: diff --git a/vllm/distributed/parallel_state.py b/vllm/distributed/parallel_state.py index 7fe9b68d4..c5c5dfbba 100644 --- a/vllm/distributed/parallel_state.py +++ b/vllm/distributed/parallel_state.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Copyright 2023 The vLLM team. # Adapted from # https://github.com/NVIDIA/Megatron-LM/blob/main/megatron/core/parallel_state.py diff --git a/vllm/distributed/utils.py b/vllm/distributed/utils.py index dcfcb848c..84f8c0a8e 100644 --- a/vllm/distributed/utils.py +++ b/vllm/distributed/utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Copyright 2023 The vLLM team. # Adapted from # https://github.com/NVIDIA/Megatron-LM/blob/main/megatron/core/tensor_parallel/utils.py diff --git a/vllm/engine/arg_utils.py b/vllm/engine/arg_utils.py index cc7c99e50..7c0e8c214 100644 --- a/vllm/engine/arg_utils.py +++ b/vllm/engine/arg_utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import argparse import dataclasses import json diff --git a/vllm/engine/async_llm_engine.py b/vllm/engine/async_llm_engine.py index 739ea06ae..053635a28 100644 --- a/vllm/engine/async_llm_engine.py +++ b/vllm/engine/async_llm_engine.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import asyncio import copy import time diff --git a/vllm/engine/async_timeout.py b/vllm/engine/async_timeout.py index 4b1842625..aa54c0693 100644 --- a/vllm/engine/async_timeout.py +++ b/vllm/engine/async_timeout.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Workaround for https://github.com/python/cpython/issues/86296 # # From https://github.com/aio-libs/async-timeout/blob/master/async_timeout/__init__.py diff --git a/vllm/engine/llm_engine.py b/vllm/engine/llm_engine.py index dd677300f..d82d9ad9d 100644 --- a/vllm/engine/llm_engine.py +++ b/vllm/engine/llm_engine.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import copy import time from collections import Counter as collectionsCounter diff --git a/vllm/engine/metrics.py b/vllm/engine/metrics.py index b771c190d..ce806b4a9 100644 --- a/vllm/engine/metrics.py +++ b/vllm/engine/metrics.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import time from typing import TYPE_CHECKING from typing import Counter as CollectionsCounter diff --git a/vllm/engine/metrics_types.py b/vllm/engine/metrics_types.py index 5c7a430d1..7f0c2fa70 100644 --- a/vllm/engine/metrics_types.py +++ b/vllm/engine/metrics_types.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """ These types are defined in this file to avoid importing vllm.engine.metrics and therefore importing prometheus_client. diff --git a/vllm/engine/multiprocessing/__init__.py b/vllm/engine/multiprocessing/__init__.py index d9703b820..3cf1850ee 100644 --- a/vllm/engine/multiprocessing/__init__.py +++ b/vllm/engine/multiprocessing/__init__.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import uuid from dataclasses import dataclass, field from enum import Enum diff --git a/vllm/engine/multiprocessing/client.py b/vllm/engine/multiprocessing/client.py index 5237f63c3..85b5f31e3 100644 --- a/vllm/engine/multiprocessing/client.py +++ b/vllm/engine/multiprocessing/client.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import asyncio import copy import pickle diff --git a/vllm/engine/multiprocessing/engine.py b/vllm/engine/multiprocessing/engine.py index 166f89743..a0dd79586 100644 --- a/vllm/engine/multiprocessing/engine.py +++ b/vllm/engine/multiprocessing/engine.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import pickle import signal from contextlib import contextmanager diff --git a/vllm/engine/output_processor/interfaces.py b/vllm/engine/output_processor/interfaces.py index 50adaf4e5..4c8e295c1 100644 --- a/vllm/engine/output_processor/interfaces.py +++ b/vllm/engine/output_processor/interfaces.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from abc import ABC, abstractmethod from typing import Callable, List diff --git a/vllm/engine/output_processor/multi_step.py b/vllm/engine/output_processor/multi_step.py index 99c2baf3f..8ceef855e 100644 --- a/vllm/engine/output_processor/multi_step.py +++ b/vllm/engine/output_processor/multi_step.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import functools from typing import Callable, List, cast diff --git a/vllm/engine/output_processor/single_step.py b/vllm/engine/output_processor/single_step.py index 55c56abea..4d96791a1 100644 --- a/vllm/engine/output_processor/single_step.py +++ b/vllm/engine/output_processor/single_step.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List from vllm.config import SchedulerConfig diff --git a/vllm/engine/output_processor/stop_checker.py b/vllm/engine/output_processor/stop_checker.py index 4b701f815..3bca0bee3 100644 --- a/vllm/engine/output_processor/stop_checker.py +++ b/vllm/engine/output_processor/stop_checker.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Callable, List, Optional, Tuple from vllm.lora.request import LoRARequest diff --git a/vllm/engine/output_processor/util.py b/vllm/engine/output_processor/util.py index 770982a20..0d2b58c10 100644 --- a/vllm/engine/output_processor/util.py +++ b/vllm/engine/output_processor/util.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List from typing import Sequence as GenericSequence from typing import cast diff --git a/vllm/engine/protocol.py b/vllm/engine/protocol.py index de7b2c1b9..d11125586 100644 --- a/vllm/engine/protocol.py +++ b/vllm/engine/protocol.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import asyncio from abc import ABC, abstractmethod from typing import AsyncGenerator, List, Mapping, Optional diff --git a/vllm/entrypoints/api_server.py b/vllm/entrypoints/api_server.py index daefbff7e..96818507d 100644 --- a/vllm/entrypoints/api_server.py +++ b/vllm/entrypoints/api_server.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """ NOTE: This API server is used only for demonstrating usage of AsyncEngine and simple performance benchmarks. It is not intended for production use. diff --git a/vllm/entrypoints/chat_utils.py b/vllm/entrypoints/chat_utils.py index 97d2561df..3a6e75b1d 100644 --- a/vllm/entrypoints/chat_utils.py +++ b/vllm/entrypoints/chat_utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import asyncio import codecs import json diff --git a/vllm/entrypoints/launcher.py b/vllm/entrypoints/launcher.py index 5dcf50bd1..351a39525 100644 --- a/vllm/entrypoints/launcher.py +++ b/vllm/entrypoints/launcher.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import asyncio import signal from http import HTTPStatus diff --git a/vllm/entrypoints/llm.py b/vllm/entrypoints/llm.py index 46b595b0d..d071a0b3c 100644 --- a/vllm/entrypoints/llm.py +++ b/vllm/entrypoints/llm.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import itertools import warnings from contextlib import contextmanager diff --git a/vllm/entrypoints/logger.py b/vllm/entrypoints/logger.py index 584ee0d9e..e82b6ba6c 100644 --- a/vllm/entrypoints/logger.py +++ b/vllm/entrypoints/logger.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List, Optional, Union from vllm.logger import init_logger diff --git a/vllm/entrypoints/openai/api_server.py b/vllm/entrypoints/openai/api_server.py index 9e5cf4ba2..b8f54d6c7 100644 --- a/vllm/entrypoints/openai/api_server.py +++ b/vllm/entrypoints/openai/api_server.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import asyncio import atexit import gc diff --git a/vllm/entrypoints/openai/cli_args.py b/vllm/entrypoints/openai/cli_args.py index 9cfe07c65..3054958f3 100644 --- a/vllm/entrypoints/openai/cli_args.py +++ b/vllm/entrypoints/openai/cli_args.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """ This file contains the command line arguments for the vLLM's OpenAI-compatible server. It is kept in a separate file for documentation diff --git a/vllm/entrypoints/openai/logits_processors.py b/vllm/entrypoints/openai/logits_processors.py index c8132811d..41e5eef40 100644 --- a/vllm/entrypoints/openai/logits_processors.py +++ b/vllm/entrypoints/openai/logits_processors.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from functools import lru_cache, partial from typing import Dict, FrozenSet, Iterable, List, Optional, Union diff --git a/vllm/entrypoints/openai/protocol.py b/vllm/entrypoints/openai/protocol.py index 29d071ce5..83b841826 100644 --- a/vllm/entrypoints/openai/protocol.py +++ b/vllm/entrypoints/openai/protocol.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Adapted from # https://github.com/lm-sys/FastChat/blob/168ccc29d3f7edc50823016105c024fe2282732a/fastchat/protocol/openai_api_protocol.py import re diff --git a/vllm/entrypoints/openai/reasoning_parsers/__init__.py b/vllm/entrypoints/openai/reasoning_parsers/__init__.py index a21bff52f..80354d69b 100644 --- a/vllm/entrypoints/openai/reasoning_parsers/__init__.py +++ b/vllm/entrypoints/openai/reasoning_parsers/__init__.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from .abs_reasoning_parsers import ReasoningParser, ReasoningParserManager from .deepseek_r1_reasoning_parser import DeepSeekR1ReasoningParser diff --git a/vllm/entrypoints/openai/reasoning_parsers/abs_reasoning_parsers.py b/vllm/entrypoints/openai/reasoning_parsers/abs_reasoning_parsers.py index e5d10ee0b..b5df7e474 100644 --- a/vllm/entrypoints/openai/reasoning_parsers/abs_reasoning_parsers.py +++ b/vllm/entrypoints/openai/reasoning_parsers/abs_reasoning_parsers.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import os from functools import cached_property from typing import Callable, Dict, List, Optional, Sequence, Tuple, Type, Union diff --git a/vllm/entrypoints/openai/reasoning_parsers/deepseek_r1_reasoning_parser.py b/vllm/entrypoints/openai/reasoning_parsers/deepseek_r1_reasoning_parser.py index a440ddc8d..5c19888d4 100644 --- a/vllm/entrypoints/openai/reasoning_parsers/deepseek_r1_reasoning_parser.py +++ b/vllm/entrypoints/openai/reasoning_parsers/deepseek_r1_reasoning_parser.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import re from typing import Optional, Sequence, Tuple, Union diff --git a/vllm/entrypoints/openai/run_batch.py b/vllm/entrypoints/openai/run_batch.py index 37ae23506..675d3cdcf 100644 --- a/vllm/entrypoints/openai/run_batch.py +++ b/vllm/entrypoints/openai/run_batch.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import asyncio from http import HTTPStatus from io import StringIO diff --git a/vllm/entrypoints/openai/serving_chat.py b/vllm/entrypoints/openai/serving_chat.py index dc97f0eb0..107220d54 100644 --- a/vllm/entrypoints/openai/serving_chat.py +++ b/vllm/entrypoints/openai/serving_chat.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import asyncio import json import time diff --git a/vllm/entrypoints/openai/serving_completion.py b/vllm/entrypoints/openai/serving_completion.py index 13c392636..e7ad263e7 100644 --- a/vllm/entrypoints/openai/serving_completion.py +++ b/vllm/entrypoints/openai/serving_completion.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import asyncio import time from typing import AsyncGenerator, AsyncIterator, Dict, List, Optional diff --git a/vllm/entrypoints/openai/serving_embedding.py b/vllm/entrypoints/openai/serving_embedding.py index e7116a3d9..45f8ad90d 100644 --- a/vllm/entrypoints/openai/serving_embedding.py +++ b/vllm/entrypoints/openai/serving_embedding.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import asyncio import base64 import time diff --git a/vllm/entrypoints/openai/serving_engine.py b/vllm/entrypoints/openai/serving_engine.py index 8d54164e5..8d39fdcb7 100644 --- a/vllm/entrypoints/openai/serving_engine.py +++ b/vllm/entrypoints/openai/serving_engine.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import json from concurrent.futures.thread import ThreadPoolExecutor from http import HTTPStatus diff --git a/vllm/entrypoints/openai/serving_models.py b/vllm/entrypoints/openai/serving_models.py index 22e74b387..f917a4851 100644 --- a/vllm/entrypoints/openai/serving_models.py +++ b/vllm/entrypoints/openai/serving_models.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import json import pathlib from dataclasses import dataclass diff --git a/vllm/entrypoints/openai/serving_pooling.py b/vllm/entrypoints/openai/serving_pooling.py index 583032207..01a3d211f 100644 --- a/vllm/entrypoints/openai/serving_pooling.py +++ b/vllm/entrypoints/openai/serving_pooling.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import asyncio import base64 import time diff --git a/vllm/entrypoints/openai/serving_rerank.py b/vllm/entrypoints/openai/serving_rerank.py index be4420261..366df7121 100644 --- a/vllm/entrypoints/openai/serving_rerank.py +++ b/vllm/entrypoints/openai/serving_rerank.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import asyncio from typing import Any, AsyncGenerator, Dict, List, Optional, Union, cast diff --git a/vllm/entrypoints/openai/serving_score.py b/vllm/entrypoints/openai/serving_score.py index 381edf8fa..832aa8516 100644 --- a/vllm/entrypoints/openai/serving_score.py +++ b/vllm/entrypoints/openai/serving_score.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import asyncio import time from typing import Any, AsyncGenerator, Dict, List, Optional, Union, cast diff --git a/vllm/entrypoints/openai/serving_tokenization.py b/vllm/entrypoints/openai/serving_tokenization.py index b67ecfb01..6c79adf90 100644 --- a/vllm/entrypoints/openai/serving_tokenization.py +++ b/vllm/entrypoints/openai/serving_tokenization.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Final, List, Optional, Union from fastapi import Request diff --git a/vllm/entrypoints/openai/tool_parsers/__init__.py b/vllm/entrypoints/openai/tool_parsers/__init__.py index 2850349a4..d1c3afa64 100644 --- a/vllm/entrypoints/openai/tool_parsers/__init__.py +++ b/vllm/entrypoints/openai/tool_parsers/__init__.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from .abstract_tool_parser import ToolParser, ToolParserManager from .granite_20b_fc_tool_parser import Granite20bFCToolParser from .granite_tool_parser import GraniteToolParser diff --git a/vllm/entrypoints/openai/tool_parsers/abstract_tool_parser.py b/vllm/entrypoints/openai/tool_parsers/abstract_tool_parser.py index aa7c20109..7cdd6d4c4 100644 --- a/vllm/entrypoints/openai/tool_parsers/abstract_tool_parser.py +++ b/vllm/entrypoints/openai/tool_parsers/abstract_tool_parser.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import os from functools import cached_property from typing import Callable, Dict, List, Optional, Sequence, Type, Union diff --git a/vllm/entrypoints/openai/tool_parsers/granite_20b_fc_tool_parser.py b/vllm/entrypoints/openai/tool_parsers/granite_20b_fc_tool_parser.py index 93e357e8b..002bf1738 100644 --- a/vllm/entrypoints/openai/tool_parsers/granite_20b_fc_tool_parser.py +++ b/vllm/entrypoints/openai/tool_parsers/granite_20b_fc_tool_parser.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import json import re from json import JSONDecoder diff --git a/vllm/entrypoints/openai/tool_parsers/granite_tool_parser.py b/vllm/entrypoints/openai/tool_parsers/granite_tool_parser.py index 8aefcd8d5..c948ed78f 100644 --- a/vllm/entrypoints/openai/tool_parsers/granite_tool_parser.py +++ b/vllm/entrypoints/openai/tool_parsers/granite_tool_parser.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import json from typing import Dict, Sequence, Union diff --git a/vllm/entrypoints/openai/tool_parsers/hermes_tool_parser.py b/vllm/entrypoints/openai/tool_parsers/hermes_tool_parser.py index 869d15ac3..4841b2870 100644 --- a/vllm/entrypoints/openai/tool_parsers/hermes_tool_parser.py +++ b/vllm/entrypoints/openai/tool_parsers/hermes_tool_parser.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import json import re from typing import Dict, List, Sequence, Union diff --git a/vllm/entrypoints/openai/tool_parsers/internlm2_tool_parser.py b/vllm/entrypoints/openai/tool_parsers/internlm2_tool_parser.py index cb391e11b..b9215e797 100644 --- a/vllm/entrypoints/openai/tool_parsers/internlm2_tool_parser.py +++ b/vllm/entrypoints/openai/tool_parsers/internlm2_tool_parser.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import json from typing import Dict, Sequence, Union diff --git a/vllm/entrypoints/openai/tool_parsers/jamba_tool_parser.py b/vllm/entrypoints/openai/tool_parsers/jamba_tool_parser.py index cfd024853..7c4d63e18 100644 --- a/vllm/entrypoints/openai/tool_parsers/jamba_tool_parser.py +++ b/vllm/entrypoints/openai/tool_parsers/jamba_tool_parser.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import json import re from typing import Dict, List, Sequence, Union diff --git a/vllm/entrypoints/openai/tool_parsers/llama_tool_parser.py b/vllm/entrypoints/openai/tool_parsers/llama_tool_parser.py index 1856308b8..6a7b11362 100644 --- a/vllm/entrypoints/openai/tool_parsers/llama_tool_parser.py +++ b/vllm/entrypoints/openai/tool_parsers/llama_tool_parser.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import json import re from json import JSONDecoder diff --git a/vllm/entrypoints/openai/tool_parsers/mistral_tool_parser.py b/vllm/entrypoints/openai/tool_parsers/mistral_tool_parser.py index bada805dd..51354f7c9 100644 --- a/vllm/entrypoints/openai/tool_parsers/mistral_tool_parser.py +++ b/vllm/entrypoints/openai/tool_parsers/mistral_tool_parser.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import json import re from random import choices diff --git a/vllm/entrypoints/openai/tool_parsers/pythonic_tool_parser.py b/vllm/entrypoints/openai/tool_parsers/pythonic_tool_parser.py index 26da4d689..5c282b5c2 100644 --- a/vllm/entrypoints/openai/tool_parsers/pythonic_tool_parser.py +++ b/vllm/entrypoints/openai/tool_parsers/pythonic_tool_parser.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import ast import json import re diff --git a/vllm/entrypoints/openai/tool_parsers/utils.py b/vllm/entrypoints/openai/tool_parsers/utils.py index 5e4eb23bf..945cbd683 100644 --- a/vllm/entrypoints/openai/tool_parsers/utils.py +++ b/vllm/entrypoints/openai/tool_parsers/utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import json from json import JSONDecodeError, JSONDecoder from typing import Any, List, Tuple diff --git a/vllm/entrypoints/utils.py b/vllm/entrypoints/utils.py index e8a78d216..9af37871d 100644 --- a/vllm/entrypoints/utils.py +++ b/vllm/entrypoints/utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import asyncio import functools diff --git a/vllm/envs.py b/vllm/envs.py index 25098070b..78ee3047b 100644 --- a/vllm/envs.py +++ b/vllm/envs.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import os import tempfile from typing import TYPE_CHECKING, Any, Callable, Dict, List, Optional diff --git a/vllm/executor/executor_base.py b/vllm/executor/executor_base.py index 471d1bfac..fb76276bb 100644 --- a/vllm/executor/executor_base.py +++ b/vllm/executor/executor_base.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import asyncio from abc import ABC, abstractmethod from typing import (Any, Awaitable, Callable, Dict, List, Optional, Set, Tuple, diff --git a/vllm/executor/mp_distributed_executor.py b/vllm/executor/mp_distributed_executor.py index 78c86321d..d1f8c36fb 100644 --- a/vllm/executor/mp_distributed_executor.py +++ b/vllm/executor/mp_distributed_executor.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import asyncio import os from typing import Any, Callable, List, Optional, Union diff --git a/vllm/executor/msgspec_utils.py b/vllm/executor/msgspec_utils.py index c467115f1..e680d53cb 100644 --- a/vllm/executor/msgspec_utils.py +++ b/vllm/executor/msgspec_utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from array import array from typing import Any, Type diff --git a/vllm/executor/multiproc_worker_utils.py b/vllm/executor/multiproc_worker_utils.py index 539b6ae2d..cef6a994a 100644 --- a/vllm/executor/multiproc_worker_utils.py +++ b/vllm/executor/multiproc_worker_utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import asyncio import os import sys diff --git a/vllm/executor/ray_distributed_executor.py b/vllm/executor/ray_distributed_executor.py index 2afd99f99..80e7a1c40 100644 --- a/vllm/executor/ray_distributed_executor.py +++ b/vllm/executor/ray_distributed_executor.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import asyncio import os from collections import defaultdict diff --git a/vllm/executor/ray_utils.py b/vllm/executor/ray_utils.py index e55155ea0..5d5cc8398 100644 --- a/vllm/executor/ray_utils.py +++ b/vllm/executor/ray_utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import os import time from collections import defaultdict diff --git a/vllm/executor/uniproc_executor.py b/vllm/executor/uniproc_executor.py index a5c4dcf0e..dcb4a8f27 100644 --- a/vllm/executor/uniproc_executor.py +++ b/vllm/executor/uniproc_executor.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import os from typing import Any, Callable, Dict, List, Optional, Tuple, Union diff --git a/vllm/forward_context.py b/vllm/forward_context.py index 828b394ec..10de8bc59 100644 --- a/vllm/forward_context.py +++ b/vllm/forward_context.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import time from collections import defaultdict from contextlib import contextmanager diff --git a/vllm/inputs/__init__.py b/vllm/inputs/__init__.py index a0dd89f69..6f8f2cd75 100644 --- a/vllm/inputs/__init__.py +++ b/vllm/inputs/__init__.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from .data import (DecoderOnlyInputs, EncoderDecoderInputs, ExplicitEncoderDecoderPrompt, ProcessorInputs, PromptType, SingletonInputs, SingletonInputsAdapter, SingletonPrompt, diff --git a/vllm/inputs/data.py b/vllm/inputs/data.py index 57e85779d..2ffebeee3 100644 --- a/vllm/inputs/data.py +++ b/vllm/inputs/data.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from dataclasses import dataclass from functools import cached_property from typing import (TYPE_CHECKING, Any, Dict, Generic, Iterable, List, Literal, diff --git a/vllm/inputs/parse.py b/vllm/inputs/parse.py index 09f1ff2cb..454d9d830 100644 --- a/vllm/inputs/parse.py +++ b/vllm/inputs/parse.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List, Literal, Sequence, TypedDict, Union, cast, overload from typing_extensions import TypeIs diff --git a/vllm/inputs/preprocess.py b/vllm/inputs/preprocess.py index 70372e0ca..4d8f28cb0 100644 --- a/vllm/inputs/preprocess.py +++ b/vllm/inputs/preprocess.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import asyncio from typing import List, Mapping, Optional, Union diff --git a/vllm/inputs/registry.py b/vllm/inputs/registry.py index 4b73ade7a..0ec726b8b 100644 --- a/vllm/inputs/registry.py +++ b/vllm/inputs/registry.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import functools from collections import UserDict from dataclasses import dataclass diff --git a/vllm/logger.py b/vllm/logger.py index cac174f7b..b20d55e3c 100644 --- a/vllm/logger.py +++ b/vllm/logger.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Logging configuration for vLLM.""" import datetime import json diff --git a/vllm/logging_utils/__init__.py b/vllm/logging_utils/__init__.py index 576ccf78a..7ab463258 100644 --- a/vllm/logging_utils/__init__.py +++ b/vllm/logging_utils/__init__.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from vllm.logging_utils.formatter import NewLineFormatter __all__ = [ diff --git a/vllm/logging_utils/formatter.py b/vllm/logging_utils/formatter.py index b24b4e11d..010b0a124 100644 --- a/vllm/logging_utils/formatter.py +++ b/vllm/logging_utils/formatter.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import logging diff --git a/vllm/logits_process.py b/vllm/logits_process.py index 7716ccd27..d02072e8f 100644 --- a/vllm/logits_process.py +++ b/vllm/logits_process.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Callable, List, Tuple, Union import torch diff --git a/vllm/lora/fully_sharded_layers.py b/vllm/lora/fully_sharded_layers.py index 545ec21ca..3d6620817 100644 --- a/vllm/lora/fully_sharded_layers.py +++ b/vllm/lora/fully_sharded_layers.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # pylint: disable=unused-argument from typing import TYPE_CHECKING, List, Optional, Tuple, Union, cast diff --git a/vllm/lora/layers.py b/vllm/lora/layers.py index cdd439d03..9f0297596 100644 --- a/vllm/lora/layers.py +++ b/vllm/lora/layers.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # pylint: disable=unused-argument import math from dataclasses import dataclass diff --git a/vllm/lora/lora.py b/vllm/lora/lora.py index 93ad4651f..00299bf6c 100644 --- a/vllm/lora/lora.py +++ b/vllm/lora/lora.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List, Optional from typing import Sequence as GenericSequence diff --git a/vllm/lora/models.py b/vllm/lora/models.py index 2e04cb902..ef77fd4b7 100644 --- a/vllm/lora/models.py +++ b/vllm/lora/models.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import copy import math import os diff --git a/vllm/lora/ops/torch_ops/__init__.py b/vllm/lora/ops/torch_ops/__init__.py index 9c9159b95..85601d58c 100644 --- a/vllm/lora/ops/torch_ops/__init__.py +++ b/vllm/lora/ops/torch_ops/__init__.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from vllm.lora.ops.torch_ops.lora_ops import bgmv_expand # noqa: F401 from vllm.lora.ops.torch_ops.lora_ops import (bgmv_expand_slice, bgmv_shrink, sgmv_expand, sgmv_expand_slice, diff --git a/vllm/lora/ops/torch_ops/lora_ops.py b/vllm/lora/ops/torch_ops/lora_ops.py index 5f5aafd51..af79f9841 100644 --- a/vllm/lora/ops/torch_ops/lora_ops.py +++ b/vllm/lora/ops/torch_ops/lora_ops.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import torch diff --git a/vllm/lora/ops/triton_ops/__init__.py b/vllm/lora/ops/triton_ops/__init__.py index 9805b6dd5..dc440f732 100644 --- a/vllm/lora/ops/triton_ops/__init__.py +++ b/vllm/lora/ops/triton_ops/__init__.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from vllm.lora.ops.triton_ops.bgmv_expand import bgmv_expand from vllm.lora.ops.triton_ops.bgmv_expand_slice import bgmv_expand_slice from vllm.lora.ops.triton_ops.bgmv_shrink import bgmv_shrink diff --git a/vllm/lora/ops/triton_ops/bgmv_expand.py b/vllm/lora/ops/triton_ops/bgmv_expand.py index 42adb191b..98510b396 100644 --- a/vllm/lora/ops/triton_ops/bgmv_expand.py +++ b/vllm/lora/ops/triton_ops/bgmv_expand.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """ Based on: Chen, L., Ye, Z., Wu, Y., Zhuo, D., Ceze, L., & Krishnamurthy, A. (2023). diff --git a/vllm/lora/ops/triton_ops/bgmv_expand_slice.py b/vllm/lora/ops/triton_ops/bgmv_expand_slice.py index f397d752a..48804123c 100644 --- a/vllm/lora/ops/triton_ops/bgmv_expand_slice.py +++ b/vllm/lora/ops/triton_ops/bgmv_expand_slice.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """ Based on: Chen, L., Ye, Z., Wu, Y., Zhuo, D., Ceze, L., & Krishnamurthy, A. (2023). diff --git a/vllm/lora/ops/triton_ops/bgmv_shrink.py b/vllm/lora/ops/triton_ops/bgmv_shrink.py index f3ef01d39..227a5765e 100644 --- a/vllm/lora/ops/triton_ops/bgmv_shrink.py +++ b/vllm/lora/ops/triton_ops/bgmv_shrink.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """ Based on: Chen, L., Ye, Z., Wu, Y., Zhuo, D., Ceze, L., & Krishnamurthy, A. (2023). diff --git a/vllm/lora/ops/triton_ops/sgmv_expand.py b/vllm/lora/ops/triton_ops/sgmv_expand.py index 48fa5cd63..a8e71cacf 100644 --- a/vllm/lora/ops/triton_ops/sgmv_expand.py +++ b/vllm/lora/ops/triton_ops/sgmv_expand.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """ Based on: Chen, L., Ye, Z., Wu, Y., Zhuo, D., Ceze, L., & Krishnamurthy, A. (2023). diff --git a/vllm/lora/ops/triton_ops/sgmv_shrink.py b/vllm/lora/ops/triton_ops/sgmv_shrink.py index 9bb35e8ff..8b26583c1 100644 --- a/vllm/lora/ops/triton_ops/sgmv_shrink.py +++ b/vllm/lora/ops/triton_ops/sgmv_shrink.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """ Based on: Chen, L., Ye, Z., Wu, Y., Zhuo, D., Ceze, L., & Krishnamurthy, A. (2023). diff --git a/vllm/lora/ops/triton_ops/utils.py b/vllm/lora/ops/triton_ops/utils.py index 7df5bc2c2..78409b91a 100644 --- a/vllm/lora/ops/triton_ops/utils.py +++ b/vllm/lora/ops/triton_ops/utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import functools from typing import Dict, List, Tuple diff --git a/vllm/lora/peft_helper.py b/vllm/lora/peft_helper.py index b9c506f6e..9496ab5a7 100644 --- a/vllm/lora/peft_helper.py +++ b/vllm/lora/peft_helper.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Adapted from: https://github.com/huggingface/peft/blob/main/src/peft/tuners/lora/config.py import json diff --git a/vllm/lora/punica_wrapper/__init__.py b/vllm/lora/punica_wrapper/__init__.py index 48ada3926..915fc6623 100644 --- a/vllm/lora/punica_wrapper/__init__.py +++ b/vllm/lora/punica_wrapper/__init__.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from vllm.lora.punica_wrapper.punica_base import PunicaWrapperBase from vllm.lora.punica_wrapper.punica_selector import get_punica_wrapper diff --git a/vllm/lora/punica_wrapper/punica_base.py b/vllm/lora/punica_wrapper/punica_base.py index b9ec0c4bc..1a2282ae9 100644 --- a/vllm/lora/punica_wrapper/punica_base.py +++ b/vllm/lora/punica_wrapper/punica_base.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """ Based on: Chen, L., Ye, Z., Wu, Y., Zhuo, D., Ceze, L., & Krishnamurthy, A. (2023). diff --git a/vllm/lora/punica_wrapper/punica_cpu.py b/vllm/lora/punica_wrapper/punica_cpu.py index b9ae3e074..29428f4cf 100644 --- a/vllm/lora/punica_wrapper/punica_cpu.py +++ b/vllm/lora/punica_wrapper/punica_cpu.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Callable, Optional, Tuple, Union import torch diff --git a/vllm/lora/punica_wrapper/punica_gpu.py b/vllm/lora/punica_wrapper/punica_gpu.py index 451f23e49..9ccd9c36a 100644 --- a/vllm/lora/punica_wrapper/punica_gpu.py +++ b/vllm/lora/punica_wrapper/punica_gpu.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """ Based on: Chen, L., Ye, Z., Wu, Y., Zhuo, D., Ceze, L., & Krishnamurthy, A. (2023). diff --git a/vllm/lora/punica_wrapper/punica_hpu.py b/vllm/lora/punica_wrapper/punica_hpu.py index d9c4f44a1..51e1bfab3 100644 --- a/vllm/lora/punica_wrapper/punica_hpu.py +++ b/vllm/lora/punica_wrapper/punica_hpu.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Optional, Tuple, Union, final import torch diff --git a/vllm/lora/punica_wrapper/punica_selector.py b/vllm/lora/punica_wrapper/punica_selector.py index a29322465..ad5d4b788 100644 --- a/vllm/lora/punica_wrapper/punica_selector.py +++ b/vllm/lora/punica_wrapper/punica_selector.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from vllm.logger import init_logger from vllm.platforms import current_platform from vllm.utils import resolve_obj_by_qualname diff --git a/vllm/lora/punica_wrapper/utils.py b/vllm/lora/punica_wrapper/utils.py index 7360c8c09..dbc2d27c5 100644 --- a/vllm/lora/punica_wrapper/utils.py +++ b/vllm/lora/punica_wrapper/utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import TYPE_CHECKING, List, Optional, Tuple, Union import torch diff --git a/vllm/lora/request.py b/vllm/lora/request.py index 5e3d2f0ed..badfaa419 100644 --- a/vllm/lora/request.py +++ b/vllm/lora/request.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import warnings from typing import Optional diff --git a/vllm/lora/utils.py b/vllm/lora/utils.py index d72b7638d..f47b0af15 100644 --- a/vllm/lora/utils.py +++ b/vllm/lora/utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import os import re from typing import List, Optional, Set, Tuple, Type, Union diff --git a/vllm/lora/worker_manager.py b/vllm/lora/worker_manager.py index a64296f7f..f33a7b88c 100644 --- a/vllm/lora/worker_manager.py +++ b/vllm/lora/worker_manager.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from contextlib import contextmanager from typing import Any, Dict, List, Literal, Optional, Set, Type, Union diff --git a/vllm/model_executor/__init__.py b/vllm/model_executor/__init__.py index 7278c7fbe..763615217 100644 --- a/vllm/model_executor/__init__.py +++ b/vllm/model_executor/__init__.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from vllm.model_executor.parameter import (BasevLLMParameter, PackedvLLMParameter) from vllm.model_executor.sampling_metadata import (SamplingMetadata, diff --git a/vllm/model_executor/custom_op.py b/vllm/model_executor/custom_op.py index 96995c56b..ee4f41ea6 100644 --- a/vllm/model_executor/custom_op.py +++ b/vllm/model_executor/custom_op.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Dict, Type import torch.nn as nn diff --git a/vllm/model_executor/guided_decoding/__init__.py b/vllm/model_executor/guided_decoding/__init__.py index 18b435a42..cf96461a5 100644 --- a/vllm/model_executor/guided_decoding/__init__.py +++ b/vllm/model_executor/guided_decoding/__init__.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from __future__ import annotations from typing import TYPE_CHECKING diff --git a/vllm/model_executor/guided_decoding/guided_fields.py b/vllm/model_executor/guided_decoding/guided_fields.py index 8deb4c949..db4ce2680 100644 --- a/vllm/model_executor/guided_decoding/guided_fields.py +++ b/vllm/model_executor/guided_decoding/guided_fields.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from dataclasses import dataclass from typing import Dict, List, Optional, TypedDict, Union diff --git a/vllm/model_executor/guided_decoding/lm_format_enforcer_decoding.py b/vllm/model_executor/guided_decoding/lm_format_enforcer_decoding.py index a17e75a80..7eaf9e38e 100644 --- a/vllm/model_executor/guided_decoding/lm_format_enforcer_decoding.py +++ b/vllm/model_executor/guided_decoding/lm_format_enforcer_decoding.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from functools import lru_cache from json import loads as json_loads from typing import Optional, Union diff --git a/vllm/model_executor/guided_decoding/outlines_decoding.py b/vllm/model_executor/guided_decoding/outlines_decoding.py index eb8db8824..ba9c98290 100644 --- a/vllm/model_executor/guided_decoding/outlines_decoding.py +++ b/vllm/model_executor/guided_decoding/outlines_decoding.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import asyncio import concurrent.futures import os diff --git a/vllm/model_executor/guided_decoding/outlines_logits_processors.py b/vllm/model_executor/guided_decoding/outlines_logits_processors.py index e4eb3f16e..ab72b55a8 100644 --- a/vllm/model_executor/guided_decoding/outlines_logits_processors.py +++ b/vllm/model_executor/guided_decoding/outlines_logits_processors.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Copyright 2024- the Outlines developers # This file is adapted from # https://github.com/outlines-dev/outlines/blob/main/outlines/serve/vllm.py diff --git a/vllm/model_executor/guided_decoding/utils.py b/vllm/model_executor/guided_decoding/utils.py index 90dfa62ec..87ef45358 100644 --- a/vllm/model_executor/guided_decoding/utils.py +++ b/vllm/model_executor/guided_decoding/utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import re diff --git a/vllm/model_executor/guided_decoding/xgrammar_decoding.py b/vllm/model_executor/guided_decoding/xgrammar_decoding.py index ee30ce96f..c01bd3af1 100644 --- a/vllm/model_executor/guided_decoding/xgrammar_decoding.py +++ b/vllm/model_executor/guided_decoding/xgrammar_decoding.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # noqa: UP007 from __future__ import annotations diff --git a/vllm/model_executor/layers/activation.py b/vllm/model_executor/layers/activation.py index fb9684ac1..f782920d0 100644 --- a/vllm/model_executor/layers/activation.py +++ b/vllm/model_executor/layers/activation.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Custom activation functions.""" import math from typing import Optional diff --git a/vllm/model_executor/layers/fused_moe/__init__.py b/vllm/model_executor/layers/fused_moe/__init__.py index c4223d126..6f933c3fa 100644 --- a/vllm/model_executor/layers/fused_moe/__init__.py +++ b/vllm/model_executor/layers/fused_moe/__init__.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from contextlib import contextmanager from typing import Any, Dict, Optional diff --git a/vllm/model_executor/layers/fused_moe/fused_marlin_moe.py b/vllm/model_executor/layers/fused_moe/fused_marlin_moe.py index 87993267c..4ca569ca4 100644 --- a/vllm/model_executor/layers/fused_moe/fused_marlin_moe.py +++ b/vllm/model_executor/layers/fused_moe/fused_marlin_moe.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Fused MoE utilities for GPTQ.""" import functools from typing import Optional diff --git a/vllm/model_executor/layers/fused_moe/fused_moe.py b/vllm/model_executor/layers/fused_moe/fused_moe.py index c80e6bf07..9613696a0 100644 --- a/vllm/model_executor/layers/fused_moe/fused_moe.py +++ b/vllm/model_executor/layers/fused_moe/fused_moe.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Fused MoE kernel.""" import functools import json diff --git a/vllm/model_executor/layers/fused_moe/layer.py b/vllm/model_executor/layers/fused_moe/layer.py index da0ce1885..3c7ef5e00 100644 --- a/vllm/model_executor/layers/fused_moe/layer.py +++ b/vllm/model_executor/layers/fused_moe/layer.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from abc import abstractmethod from enum import Enum from typing import Callable, List, Optional, Tuple diff --git a/vllm/model_executor/layers/fused_moe/moe_pallas.py b/vllm/model_executor/layers/fused_moe/moe_pallas.py index 563ee18c6..0365afa10 100644 --- a/vllm/model_executor/layers/fused_moe/moe_pallas.py +++ b/vllm/model_executor/layers/fused_moe/moe_pallas.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import torch import torch.nn.functional as F from torch_xla.experimental.custom_kernel import _histogram diff --git a/vllm/model_executor/layers/fused_moe/moe_torch_iterative.py b/vllm/model_executor/layers/fused_moe/moe_torch_iterative.py index bcff55f4f..d9a5de1b3 100644 --- a/vllm/model_executor/layers/fused_moe/moe_torch_iterative.py +++ b/vllm/model_executor/layers/fused_moe/moe_torch_iterative.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import torch import torch.nn.functional as F diff --git a/vllm/model_executor/layers/layernorm.py b/vllm/model_executor/layers/layernorm.py index 43ea4eb5a..b476fb0db 100644 --- a/vllm/model_executor/layers/layernorm.py +++ b/vllm/model_executor/layers/layernorm.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Custom normalization layers.""" from typing import Optional, Tuple, Union diff --git a/vllm/model_executor/layers/linear.py b/vllm/model_executor/layers/linear.py index 52263e96f..08f1e103e 100644 --- a/vllm/model_executor/layers/linear.py +++ b/vllm/model_executor/layers/linear.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import itertools from abc import abstractmethod from typing import Dict, List, Optional, Tuple diff --git a/vllm/model_executor/layers/logits_processor.py b/vllm/model_executor/layers/logits_processor.py index 42decde1d..ebf74c67d 100644 --- a/vllm/model_executor/layers/logits_processor.py +++ b/vllm/model_executor/layers/logits_processor.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """A layer that compute logits from hidden_stats.""" import inspect from typing import Optional diff --git a/vllm/model_executor/layers/mamba/mamba_mixer.py b/vllm/model_executor/layers/mamba/mamba_mixer.py index 606c796d5..93c3cc91b 100644 --- a/vllm/model_executor/layers/mamba/mamba_mixer.py +++ b/vllm/model_executor/layers/mamba/mamba_mixer.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import torch from torch import nn from torch.nn.parameter import Parameter diff --git a/vllm/model_executor/layers/mamba/ops/causal_conv1d.py b/vllm/model_executor/layers/mamba/ops/causal_conv1d.py index be5639df9..21e27160f 100644 --- a/vllm/model_executor/layers/mamba/ops/causal_conv1d.py +++ b/vllm/model_executor/layers/mamba/ops/causal_conv1d.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Copyright (c) 2024, Tri Dao. # Adapted from https://github.com/Dao-AILab/causal-conv1d/blob/main/causal_conv1d/causal_conv1d_interface.py diff --git a/vllm/model_executor/layers/mamba/ops/mamba_ssm.py b/vllm/model_executor/layers/mamba/ops/mamba_ssm.py index 1484b7981..3c35f1ac0 100644 --- a/vllm/model_executor/layers/mamba/ops/mamba_ssm.py +++ b/vllm/model_executor/layers/mamba/ops/mamba_ssm.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Copyright (c) 2024, Tri Dao, Albert Gu. # Adapted from https://github.com/state-spaces/mamba/blob/main/mamba_ssm/ops/triton/selective_state_update.py diff --git a/vllm/model_executor/layers/pooler.py b/vllm/model_executor/layers/pooler.py index 75bf33dc7..0012636ef 100644 --- a/vllm/model_executor/layers/pooler.py +++ b/vllm/model_executor/layers/pooler.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from enum import IntEnum from typing import List, Optional, Union diff --git a/vllm/model_executor/layers/quantization/__init__.py b/vllm/model_executor/layers/quantization/__init__.py index bd0fd4799..6ded3874f 100644 --- a/vllm/model_executor/layers/quantization/__init__.py +++ b/vllm/model_executor/layers/quantization/__init__.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Dict, List, Type from vllm.model_executor.layers.quantization.base_config import ( diff --git a/vllm/model_executor/layers/quantization/aqlm.py b/vllm/model_executor/layers/quantization/aqlm.py index 72c89fe2b..6c08d016c 100644 --- a/vllm/model_executor/layers/quantization/aqlm.py +++ b/vllm/model_executor/layers/quantization/aqlm.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Supports AQLM compression, see https://github.com/Vahe1994/AQLM # and https://arxiv.org/pdf/2401.06118.pdf diff --git a/vllm/model_executor/layers/quantization/awq.py b/vllm/model_executor/layers/quantization/awq.py index d83528e9e..ff77af44d 100644 --- a/vllm/model_executor/layers/quantization/awq.py +++ b/vllm/model_executor/layers/quantization/awq.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Any, Dict, List, Optional import torch diff --git a/vllm/model_executor/layers/quantization/awq_marlin.py b/vllm/model_executor/layers/quantization/awq_marlin.py index 0c3c98168..8849ba292 100644 --- a/vllm/model_executor/layers/quantization/awq_marlin.py +++ b/vllm/model_executor/layers/quantization/awq_marlin.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Any, Callable, Dict, List, Optional import torch diff --git a/vllm/model_executor/layers/quantization/awq_triton.py b/vllm/model_executor/layers/quantization/awq_triton.py index ace8f4a34..09efd4dbd 100644 --- a/vllm/model_executor/layers/quantization/awq_triton.py +++ b/vllm/model_executor/layers/quantization/awq_triton.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import torch import triton import triton.language as tl diff --git a/vllm/model_executor/layers/quantization/base_config.py b/vllm/model_executor/layers/quantization/base_config.py index 2fb2642dd..2eefcc4f3 100644 --- a/vllm/model_executor/layers/quantization/base_config.py +++ b/vllm/model_executor/layers/quantization/base_config.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import inspect from abc import ABC, abstractmethod from typing import Any, Dict, List, Optional, Type diff --git a/vllm/model_executor/layers/quantization/bitsandbytes.py b/vllm/model_executor/layers/quantization/bitsandbytes.py index 5dc872933..889eda009 100644 --- a/vllm/model_executor/layers/quantization/bitsandbytes.py +++ b/vllm/model_executor/layers/quantization/bitsandbytes.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Any, Dict, List, Optional import torch diff --git a/vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors.py b/vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors.py index 37981ed91..24f7542e1 100644 --- a/vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors.py +++ b/vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from contextlib import suppress from typing import Any, Dict, List, Literal, Optional, Tuple, cast diff --git a/vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors_moe.py b/vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors_moe.py index e1c45f4e4..db8e8a4b6 100644 --- a/vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors_moe.py +++ b/vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors_moe.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import enum from enum import Enum from typing import Callable, List, Optional diff --git a/vllm/model_executor/layers/quantization/compressed_tensors/schemes/__init__.py b/vllm/model_executor/layers/quantization/compressed_tensors/schemes/__init__.py index 569ecaa6f..b26c74f24 100644 --- a/vllm/model_executor/layers/quantization/compressed_tensors/schemes/__init__.py +++ b/vllm/model_executor/layers/quantization/compressed_tensors/schemes/__init__.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from .compressed_tensors_scheme import CompressedTensorsScheme from .compressed_tensors_w4a16_24 import (W4A16SPARSE24_SUPPORTED_BITS, CompressedTensorsW4A16Sparse24) diff --git a/vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_24.py b/vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_24.py index 21e6fe7a2..84f924b23 100644 --- a/vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_24.py +++ b/vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_24.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Callable, List, Optional import torch diff --git a/vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_scheme.py b/vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_scheme.py index b4bab33e1..daa25d23a 100644 --- a/vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_scheme.py +++ b/vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_scheme.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from abc import ABC, abstractmethod from typing import Optional diff --git a/vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a16_24.py b/vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a16_24.py index 2e1b5e3c2..535ea6b32 100644 --- a/vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a16_24.py +++ b/vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a16_24.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Callable, List, Optional import torch diff --git a/vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a16_fp8.py b/vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a16_fp8.py index 1671a23d7..5c8261908 100644 --- a/vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a16_fp8.py +++ b/vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a16_fp8.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Callable, List, Optional import torch diff --git a/vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_fp8.py b/vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_fp8.py index 1d4e4bd52..5dcc41a9e 100644 --- a/vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_fp8.py +++ b/vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_fp8.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Callable, List, Optional import torch diff --git a/vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_int8.py b/vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_int8.py index 0e3f47317..08d86a4e5 100644 --- a/vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_int8.py +++ b/vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_int8.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Callable, List, Optional, Set import torch diff --git a/vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_wNa16.py b/vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_wNa16.py index 2dd243b9c..38df09ff3 100644 --- a/vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_wNa16.py +++ b/vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_wNa16.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Callable, List, Optional, Set import torch diff --git a/vllm/model_executor/layers/quantization/compressed_tensors/triton_scaled_mm.py b/vllm/model_executor/layers/quantization/compressed_tensors/triton_scaled_mm.py index f4c1dbc03..b69c5e7a0 100644 --- a/vllm/model_executor/layers/quantization/compressed_tensors/triton_scaled_mm.py +++ b/vllm/model_executor/layers/quantization/compressed_tensors/triton_scaled_mm.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Optional, Type import torch diff --git a/vllm/model_executor/layers/quantization/compressed_tensors/utils.py b/vllm/model_executor/layers/quantization/compressed_tensors/utils.py index 34996b08e..d700a0b15 100644 --- a/vllm/model_executor/layers/quantization/compressed_tensors/utils.py +++ b/vllm/model_executor/layers/quantization/compressed_tensors/utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import re from typing import Iterable, Optional diff --git a/vllm/model_executor/layers/quantization/deepspeedfp.py b/vllm/model_executor/layers/quantization/deepspeedfp.py index 36598b3e2..b41236501 100644 --- a/vllm/model_executor/layers/quantization/deepspeedfp.py +++ b/vllm/model_executor/layers/quantization/deepspeedfp.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Any, Dict, List, Optional import torch diff --git a/vllm/model_executor/layers/quantization/experts_int8.py b/vllm/model_executor/layers/quantization/experts_int8.py index 100cbfa4c..87fbcf62a 100644 --- a/vllm/model_executor/layers/quantization/experts_int8.py +++ b/vllm/model_executor/layers/quantization/experts_int8.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Any, Callable, Dict, List, Optional import torch diff --git a/vllm/model_executor/layers/quantization/fbgemm_fp8.py b/vllm/model_executor/layers/quantization/fbgemm_fp8.py index 7b71e13b5..da5ef36c5 100644 --- a/vllm/model_executor/layers/quantization/fbgemm_fp8.py +++ b/vllm/model_executor/layers/quantization/fbgemm_fp8.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Any, Dict, List, Optional import torch diff --git a/vllm/model_executor/layers/quantization/fp8.py b/vllm/model_executor/layers/quantization/fp8.py index adab1973b..86e025310 100644 --- a/vllm/model_executor/layers/quantization/fp8.py +++ b/vllm/model_executor/layers/quantization/fp8.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Any, Callable, Dict, List, Optional import torch diff --git a/vllm/model_executor/layers/quantization/gguf.py b/vllm/model_executor/layers/quantization/gguf.py index f0943efa0..86e6dbb5a 100644 --- a/vllm/model_executor/layers/quantization/gguf.py +++ b/vllm/model_executor/layers/quantization/gguf.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Any, Dict, List, Optional import gguf diff --git a/vllm/model_executor/layers/quantization/gptq.py b/vllm/model_executor/layers/quantization/gptq.py index abafad0f1..0cb77a754 100644 --- a/vllm/model_executor/layers/quantization/gptq.py +++ b/vllm/model_executor/layers/quantization/gptq.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import enum from enum import Enum from fractions import Fraction diff --git a/vllm/model_executor/layers/quantization/gptq_marlin.py b/vllm/model_executor/layers/quantization/gptq_marlin.py index 4dc4b052b..99ab29995 100644 --- a/vllm/model_executor/layers/quantization/gptq_marlin.py +++ b/vllm/model_executor/layers/quantization/gptq_marlin.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Any, Callable, Dict, List, Optional, Set, Union import torch diff --git a/vllm/model_executor/layers/quantization/gptq_marlin_24.py b/vllm/model_executor/layers/quantization/gptq_marlin_24.py index 07552c0f1..cec984483 100644 --- a/vllm/model_executor/layers/quantization/gptq_marlin_24.py +++ b/vllm/model_executor/layers/quantization/gptq_marlin_24.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Any, Dict, List, Optional import torch diff --git a/vllm/model_executor/layers/quantization/hqq_marlin.py b/vllm/model_executor/layers/quantization/hqq_marlin.py index 28538d299..432f43688 100644 --- a/vllm/model_executor/layers/quantization/hqq_marlin.py +++ b/vllm/model_executor/layers/quantization/hqq_marlin.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Any, Dict, List, Optional import torch diff --git a/vllm/model_executor/layers/quantization/ipex_quant.py b/vllm/model_executor/layers/quantization/ipex_quant.py index c16a96213..2531170ec 100644 --- a/vllm/model_executor/layers/quantization/ipex_quant.py +++ b/vllm/model_executor/layers/quantization/ipex_quant.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Any, Dict, List, Optional import torch diff --git a/vllm/model_executor/layers/quantization/kernels/mixed_precision/MPLinearKernel.py b/vllm/model_executor/layers/quantization/kernels/mixed_precision/MPLinearKernel.py index 915bdc477..c06befaf3 100644 --- a/vllm/model_executor/layers/quantization/kernels/mixed_precision/MPLinearKernel.py +++ b/vllm/model_executor/layers/quantization/kernels/mixed_precision/MPLinearKernel.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from abc import ABC, abstractmethod from dataclasses import dataclass from typing import Callable, Optional, Tuple diff --git a/vllm/model_executor/layers/quantization/kernels/mixed_precision/__init__.py b/vllm/model_executor/layers/quantization/kernels/mixed_precision/__init__.py index 83549870e..bcfdb1677 100644 --- a/vllm/model_executor/layers/quantization/kernels/mixed_precision/__init__.py +++ b/vllm/model_executor/layers/quantization/kernels/mixed_precision/__init__.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List, Optional, Type import vllm.envs as envs diff --git a/vllm/model_executor/layers/quantization/kernels/mixed_precision/exllama.py b/vllm/model_executor/layers/quantization/kernels/mixed_precision/exllama.py index 1d85d62ec..2706fbb53 100644 --- a/vllm/model_executor/layers/quantization/kernels/mixed_precision/exllama.py +++ b/vllm/model_executor/layers/quantization/kernels/mixed_precision/exllama.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Optional, Tuple import torch diff --git a/vllm/model_executor/layers/quantization/kernels/mixed_precision/machete.py b/vllm/model_executor/layers/quantization/kernels/mixed_precision/machete.py index 15df0200f..3f0586f6e 100644 --- a/vllm/model_executor/layers/quantization/kernels/mixed_precision/machete.py +++ b/vllm/model_executor/layers/quantization/kernels/mixed_precision/machete.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from functools import partial from typing import Optional, Tuple diff --git a/vllm/model_executor/layers/quantization/kernels/mixed_precision/marlin.py b/vllm/model_executor/layers/quantization/kernels/mixed_precision/marlin.py index 6969583d6..e21801cf6 100644 --- a/vllm/model_executor/layers/quantization/kernels/mixed_precision/marlin.py +++ b/vllm/model_executor/layers/quantization/kernels/mixed_precision/marlin.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Optional, Tuple import torch diff --git a/vllm/model_executor/layers/quantization/kernels/scaled_mm/ScaledMMLinearKernel.py b/vllm/model_executor/layers/quantization/kernels/scaled_mm/ScaledMMLinearKernel.py index c4a83b4fa..91e765405 100644 --- a/vllm/model_executor/layers/quantization/kernels/scaled_mm/ScaledMMLinearKernel.py +++ b/vllm/model_executor/layers/quantization/kernels/scaled_mm/ScaledMMLinearKernel.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from abc import ABC, abstractmethod from dataclasses import dataclass from typing import Optional, Tuple diff --git a/vllm/model_executor/layers/quantization/kernels/scaled_mm/__init__.py b/vllm/model_executor/layers/quantization/kernels/scaled_mm/__init__.py index 4824a1180..a5967995a 100644 --- a/vllm/model_executor/layers/quantization/kernels/scaled_mm/__init__.py +++ b/vllm/model_executor/layers/quantization/kernels/scaled_mm/__init__.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import os from typing import Dict, List, Optional, Type diff --git a/vllm/model_executor/layers/quantization/kernels/scaled_mm/cutlass.py b/vllm/model_executor/layers/quantization/kernels/scaled_mm/cutlass.py index 2e83a0428..2bf21a05c 100644 --- a/vllm/model_executor/layers/quantization/kernels/scaled_mm/cutlass.py +++ b/vllm/model_executor/layers/quantization/kernels/scaled_mm/cutlass.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Optional, Tuple import torch diff --git a/vllm/model_executor/layers/quantization/kernels/scaled_mm/triton.py b/vllm/model_executor/layers/quantization/kernels/scaled_mm/triton.py index 97ec8cb05..5da5df8ef 100644 --- a/vllm/model_executor/layers/quantization/kernels/scaled_mm/triton.py +++ b/vllm/model_executor/layers/quantization/kernels/scaled_mm/triton.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Optional, Tuple import torch diff --git a/vllm/model_executor/layers/quantization/kernels/scaled_mm/xla.py b/vllm/model_executor/layers/quantization/kernels/scaled_mm/xla.py index 9de668e65..0bf090d7f 100644 --- a/vllm/model_executor/layers/quantization/kernels/scaled_mm/xla.py +++ b/vllm/model_executor/layers/quantization/kernels/scaled_mm/xla.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import warnings from typing import Optional, Tuple diff --git a/vllm/model_executor/layers/quantization/kv_cache.py b/vllm/model_executor/layers/quantization/kv_cache.py index e1870c73c..388a4f166 100644 --- a/vllm/model_executor/layers/quantization/kv_cache.py +++ b/vllm/model_executor/layers/quantization/kv_cache.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import torch from vllm.logger import init_logger diff --git a/vllm/model_executor/layers/quantization/marlin.py b/vllm/model_executor/layers/quantization/marlin.py index 20212e672..4cf0c677c 100644 --- a/vllm/model_executor/layers/quantization/marlin.py +++ b/vllm/model_executor/layers/quantization/marlin.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Any, Dict, List, Optional import torch diff --git a/vllm/model_executor/layers/quantization/modelopt.py b/vllm/model_executor/layers/quantization/modelopt.py index a1b3eeb43..348e9bccd 100644 --- a/vllm/model_executor/layers/quantization/modelopt.py +++ b/vllm/model_executor/layers/quantization/modelopt.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Any, Dict, List, Optional import torch diff --git a/vllm/model_executor/layers/quantization/moe_wna16.py b/vllm/model_executor/layers/quantization/moe_wna16.py index 11a9d4ac5..1ae765a22 100644 --- a/vllm/model_executor/layers/quantization/moe_wna16.py +++ b/vllm/model_executor/layers/quantization/moe_wna16.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Any, Callable, Dict, List, Optional import torch diff --git a/vllm/model_executor/layers/quantization/neuron_quant.py b/vllm/model_executor/layers/quantization/neuron_quant.py index 2d5cdfa16..a8e8be207 100644 --- a/vllm/model_executor/layers/quantization/neuron_quant.py +++ b/vllm/model_executor/layers/quantization/neuron_quant.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import os from importlib.util import find_spec from typing import Any, Dict, List, Optional diff --git a/vllm/model_executor/layers/quantization/qqq.py b/vllm/model_executor/layers/quantization/qqq.py index 2ccd08202..6e9d3dc6c 100644 --- a/vllm/model_executor/layers/quantization/qqq.py +++ b/vllm/model_executor/layers/quantization/qqq.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Any, Dict, List, Optional import torch diff --git a/vllm/model_executor/layers/quantization/quark/quark.py b/vllm/model_executor/layers/quantization/quark/quark.py index fc214255e..0451cf82b 100644 --- a/vllm/model_executor/layers/quantization/quark/quark.py +++ b/vllm/model_executor/layers/quantization/quark/quark.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import fnmatch import re from typing import Any, Dict, List, Optional, cast diff --git a/vllm/model_executor/layers/quantization/quark/quark_moe.py b/vllm/model_executor/layers/quantization/quark/quark_moe.py index 68a395454..98743b15e 100644 --- a/vllm/model_executor/layers/quantization/quark/quark_moe.py +++ b/vllm/model_executor/layers/quantization/quark/quark_moe.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Any, Callable, Dict, Optional import torch diff --git a/vllm/model_executor/layers/quantization/quark/schemes/__init__.py b/vllm/model_executor/layers/quantization/quark/schemes/__init__.py index fb0ba9bd5..9069b5a0d 100644 --- a/vllm/model_executor/layers/quantization/quark/schemes/__init__.py +++ b/vllm/model_executor/layers/quantization/quark/schemes/__init__.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from .quark_scheme import QuarkScheme from .quark_w8a8_fp8 import QuarkW8A8Fp8 from .quark_w8a8_int8 import QuarkW8A8Int8 diff --git a/vllm/model_executor/layers/quantization/quark/schemes/quark_scheme.py b/vllm/model_executor/layers/quantization/quark/schemes/quark_scheme.py index 239597fa4..40c8ea86d 100644 --- a/vllm/model_executor/layers/quantization/quark/schemes/quark_scheme.py +++ b/vllm/model_executor/layers/quantization/quark/schemes/quark_scheme.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from abc import ABC, abstractmethod from typing import Optional diff --git a/vllm/model_executor/layers/quantization/quark/schemes/quark_w8a8_fp8.py b/vllm/model_executor/layers/quantization/quark/schemes/quark_w8a8_fp8.py index 206931ea2..c885e98a4 100644 --- a/vllm/model_executor/layers/quantization/quark/schemes/quark_w8a8_fp8.py +++ b/vllm/model_executor/layers/quantization/quark/schemes/quark_w8a8_fp8.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Callable, List, Optional import torch diff --git a/vllm/model_executor/layers/quantization/quark/schemes/quark_w8a8_int8.py b/vllm/model_executor/layers/quantization/quark/schemes/quark_w8a8_int8.py index 8cb47e9c3..1bf34b098 100644 --- a/vllm/model_executor/layers/quantization/quark/schemes/quark_w8a8_int8.py +++ b/vllm/model_executor/layers/quantization/quark/schemes/quark_w8a8_int8.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Callable, List, Optional, Set import torch diff --git a/vllm/model_executor/layers/quantization/quark/utils.py b/vllm/model_executor/layers/quantization/quark/utils.py index 742a629bd..afb1d9d63 100644 --- a/vllm/model_executor/layers/quantization/quark/utils.py +++ b/vllm/model_executor/layers/quantization/quark/utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import re from typing import Any, Iterable, Optional diff --git a/vllm/model_executor/layers/quantization/schema.py b/vllm/model_executor/layers/quantization/schema.py index a26c52478..026881f2d 100644 --- a/vllm/model_executor/layers/quantization/schema.py +++ b/vllm/model_executor/layers/quantization/schema.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """ This file contains the Pydantic schemas for various quantization-related parameters. When a relevant quantization technique is specified, these diff --git a/vllm/model_executor/layers/quantization/tpu_int8.py b/vllm/model_executor/layers/quantization/tpu_int8.py index 605c3a386..3234fecaa 100644 --- a/vllm/model_executor/layers/quantization/tpu_int8.py +++ b/vllm/model_executor/layers/quantization/tpu_int8.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Any, Dict, List, Optional, Tuple import torch diff --git a/vllm/model_executor/layers/quantization/utils/__init__.py b/vllm/model_executor/layers/quantization/utils/__init__.py index e60f0c79a..f7ee47288 100644 --- a/vllm/model_executor/layers/quantization/utils/__init__.py +++ b/vllm/model_executor/layers/quantization/utils/__init__.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from .layer_utils import replace_parameter, update_tensor_inplace __all__ = ['update_tensor_inplace', 'replace_parameter'] diff --git a/vllm/model_executor/layers/quantization/utils/fp8_utils.py b/vllm/model_executor/layers/quantization/utils/fp8_utils.py index 850820f66..29c7268ad 100644 --- a/vllm/model_executor/layers/quantization/utils/fp8_utils.py +++ b/vllm/model_executor/layers/quantization/utils/fp8_utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Adapted from https://github.com/sgl-project/sglang/pull/2575 import functools import json diff --git a/vllm/model_executor/layers/quantization/utils/layer_utils.py b/vllm/model_executor/layers/quantization/utils/layer_utils.py index edce6d19b..5acae7ca3 100644 --- a/vllm/model_executor/layers/quantization/utils/layer_utils.py +++ b/vllm/model_executor/layers/quantization/utils/layer_utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Union import torch diff --git a/vllm/model_executor/layers/quantization/utils/machete_utils.py b/vllm/model_executor/layers/quantization/utils/machete_utils.py index 18e133205..cb7d49ed6 100644 --- a/vllm/model_executor/layers/quantization/utils/machete_utils.py +++ b/vllm/model_executor/layers/quantization/utils/machete_utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List, Optional, Tuple import torch diff --git a/vllm/model_executor/layers/quantization/utils/marlin_utils.py b/vllm/model_executor/layers/quantization/utils/marlin_utils.py index c9366ca97..3beba3083 100644 --- a/vllm/model_executor/layers/quantization/utils/marlin_utils.py +++ b/vllm/model_executor/layers/quantization/utils/marlin_utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List, Optional, Tuple import numpy diff --git a/vllm/model_executor/layers/quantization/utils/marlin_utils_fp8.py b/vllm/model_executor/layers/quantization/utils/marlin_utils_fp8.py index 245fe9238..6120a8e66 100644 --- a/vllm/model_executor/layers/quantization/utils/marlin_utils_fp8.py +++ b/vllm/model_executor/layers/quantization/utils/marlin_utils_fp8.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Optional import torch diff --git a/vllm/model_executor/layers/quantization/utils/marlin_utils_test.py b/vllm/model_executor/layers/quantization/utils/marlin_utils_test.py index 4a06c5d63..fb557a313 100644 --- a/vllm/model_executor/layers/quantization/utils/marlin_utils_test.py +++ b/vllm/model_executor/layers/quantization/utils/marlin_utils_test.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Utility functions used for tests and benchmarks""" from typing import List, Optional diff --git a/vllm/model_executor/layers/quantization/utils/marlin_utils_test_24.py b/vllm/model_executor/layers/quantization/utils/marlin_utils_test_24.py index 17d09055b..3654268e2 100644 --- a/vllm/model_executor/layers/quantization/utils/marlin_utils_test_24.py +++ b/vllm/model_executor/layers/quantization/utils/marlin_utils_test_24.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Utility functions used for tests and benchmarks""" import random diff --git a/vllm/model_executor/layers/quantization/utils/marlin_utils_test_qqq.py b/vllm/model_executor/layers/quantization/utils/marlin_utils_test_qqq.py index cb58eb945..176b2947a 100644 --- a/vllm/model_executor/layers/quantization/utils/marlin_utils_test_qqq.py +++ b/vllm/model_executor/layers/quantization/utils/marlin_utils_test_qqq.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List import numpy diff --git a/vllm/model_executor/layers/quantization/utils/quant_utils.py b/vllm/model_executor/layers/quantization/utils/quant_utils.py index 95e785dcc..62484f62f 100644 --- a/vllm/model_executor/layers/quantization/utils/quant_utils.py +++ b/vllm/model_executor/layers/quantization/utils/quant_utils.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """This file is used for /tests and /benchmarks""" from typing import List, Optional, Tuple diff --git a/vllm/model_executor/layers/quantization/utils/w8a8_utils.py b/vllm/model_executor/layers/quantization/utils/w8a8_utils.py index 3af3b3e0e..3fd88e875 100644 --- a/vllm/model_executor/layers/quantization/utils/w8a8_utils.py +++ b/vllm/model_executor/layers/quantization/utils/w8a8_utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List, Optional, Tuple, Union import torch diff --git a/vllm/model_executor/layers/rejection_sampler.py b/vllm/model_executor/layers/rejection_sampler.py index 9d6c3797c..62e27b714 100644 --- a/vllm/model_executor/layers/rejection_sampler.py +++ b/vllm/model_executor/layers/rejection_sampler.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from functools import cached_property from importlib.util import find_spec from typing import Dict, Optional, Tuple diff --git a/vllm/model_executor/layers/resampler.py b/vllm/model_executor/layers/resampler.py index a67713c32..4c9860006 100644 --- a/vllm/model_executor/layers/resampler.py +++ b/vllm/model_executor/layers/resampler.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Adapted from # https://github.com/huggingface/transformers/blob/v4.28.0/src/transformers/models/llama/modeling_llama.py # https://huggingface.co/Qwen/Qwen-7B/blob/main/modeling_qwen.py diff --git a/vllm/model_executor/layers/rotary_embedding.py b/vllm/model_executor/layers/rotary_embedding.py index d071cfe88..814c3b7d9 100644 --- a/vllm/model_executor/layers/rotary_embedding.py +++ b/vllm/model_executor/layers/rotary_embedding.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Adapted from # https://github.com/huggingface/transformers/blob/v4.33.2/src/transformers/models/llama/modeling_llama.py # Copyright 2023 The vLLM team. diff --git a/vllm/model_executor/layers/sampler.py b/vllm/model_executor/layers/sampler.py index 8dc26309d..6af734be5 100644 --- a/vllm/model_executor/layers/sampler.py +++ b/vllm/model_executor/layers/sampler.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """A layer that samples the next tokens from the model's outputs.""" import itertools import warnings diff --git a/vllm/model_executor/layers/spec_decode_base_sampler.py b/vllm/model_executor/layers/spec_decode_base_sampler.py index 6aa4b8bd3..35c7ffec2 100644 --- a/vllm/model_executor/layers/spec_decode_base_sampler.py +++ b/vllm/model_executor/layers/spec_decode_base_sampler.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from abc import abstractmethod from typing import Dict, Optional, Union diff --git a/vllm/model_executor/layers/typical_acceptance_sampler.py b/vllm/model_executor/layers/typical_acceptance_sampler.py index 584cf971d..95362c280 100644 --- a/vllm/model_executor/layers/typical_acceptance_sampler.py +++ b/vllm/model_executor/layers/typical_acceptance_sampler.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import torch import torch.jit diff --git a/vllm/model_executor/layers/utils.py b/vllm/model_executor/layers/utils.py index f6f34cd49..dfe71028c 100644 --- a/vllm/model_executor/layers/utils.py +++ b/vllm/model_executor/layers/utils.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Utility methods for model layers.""" from typing import Tuple diff --git a/vllm/model_executor/layers/vocab_parallel_embedding.py b/vllm/model_executor/layers/vocab_parallel_embedding.py index f230efaca..e409094dd 100644 --- a/vllm/model_executor/layers/vocab_parallel_embedding.py +++ b/vllm/model_executor/layers/vocab_parallel_embedding.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from dataclasses import dataclass from typing import List, Optional, Sequence, Tuple diff --git a/vllm/model_executor/model_loader/__init__.py b/vllm/model_executor/model_loader/__init__.py index 12468997e..9048c70c7 100644 --- a/vllm/model_executor/model_loader/__init__.py +++ b/vllm/model_executor/model_loader/__init__.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from torch import nn from vllm.config import VllmConfig diff --git a/vllm/model_executor/model_loader/loader.py b/vllm/model_executor/model_loader/loader.py index 4be511d12..809af81d7 100644 --- a/vllm/model_executor/model_loader/loader.py +++ b/vllm/model_executor/model_loader/loader.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # ruff: noqa: SIM117 import collections import copy diff --git a/vllm/model_executor/model_loader/neuron.py b/vllm/model_executor/model_loader/neuron.py index a90fbd648..d900fb3a7 100644 --- a/vllm/model_executor/model_loader/neuron.py +++ b/vllm/model_executor/model_loader/neuron.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Utilities for selecting and loading neuron models.""" import copy import importlib diff --git a/vllm/model_executor/model_loader/openvino.py b/vllm/model_executor/model_loader/openvino.py index e6299295c..7bd531c56 100644 --- a/vllm/model_executor/model_loader/openvino.py +++ b/vllm/model_executor/model_loader/openvino.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # ruff: noqa: SIM117 from pathlib import Path from typing import List, Optional, Tuple diff --git a/vllm/model_executor/model_loader/tensorizer.py b/vllm/model_executor/model_loader/tensorizer.py index 9266ca75d..117251ccf 100644 --- a/vllm/model_executor/model_loader/tensorizer.py +++ b/vllm/model_executor/model_loader/tensorizer.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import argparse import dataclasses import io diff --git a/vllm/model_executor/model_loader/utils.py b/vllm/model_executor/model_loader/utils.py index 3f923d2f6..084ca53b1 100644 --- a/vllm/model_executor/model_loader/utils.py +++ b/vllm/model_executor/model_loader/utils.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Utilities for selecting and loading models.""" import contextlib from dataclasses import dataclass, field diff --git a/vllm/model_executor/model_loader/weight_utils.py b/vllm/model_executor/model_loader/weight_utils.py index e4d103f7c..cade0a1dd 100644 --- a/vllm/model_executor/model_loader/weight_utils.py +++ b/vllm/model_executor/model_loader/weight_utils.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Utilities for downloading and initializing model weights.""" import fnmatch import glob diff --git a/vllm/model_executor/models/__init__.py b/vllm/model_executor/models/__init__.py index a3ef9adad..6be4a8341 100644 --- a/vllm/model_executor/models/__init__.py +++ b/vllm/model_executor/models/__init__.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from .interfaces import (HasInnerState, SupportsLoRA, SupportsMultiModal, SupportsPP, has_inner_state, supports_lora, supports_multimodal, supports_pp) diff --git a/vllm/model_executor/models/adapters.py b/vllm/model_executor/models/adapters.py index 55e90b9d4..3e1daa773 100644 --- a/vllm/model_executor/models/adapters.py +++ b/vllm/model_executor/models/adapters.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from collections.abc import Iterable from typing import TYPE_CHECKING, Any, Optional, TypeVar diff --git a/vllm/model_executor/models/arctic.py b/vllm/model_executor/models/arctic.py index fd6b5659d..d015682aa 100644 --- a/vllm/model_executor/models/arctic.py +++ b/vllm/model_executor/models/arctic.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Inference-only Snowflake Arctic model.""" from typing import Iterable, List, Optional, Set, Tuple, Union diff --git a/vllm/model_executor/models/aria.py b/vllm/model_executor/models/aria.py index 8c6873de1..97502c38b 100644 --- a/vllm/model_executor/models/aria.py +++ b/vllm/model_executor/models/aria.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import (Iterable, List, Mapping, Optional, Set, Tuple, TypedDict, Union) diff --git a/vllm/model_executor/models/baichuan.py b/vllm/model_executor/models/baichuan.py index a923ed36a..5dfaa727b 100644 --- a/vllm/model_executor/models/baichuan.py +++ b/vllm/model_executor/models/baichuan.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Copyright 2022 EleutherAI and the HuggingFace Inc. team. All rights reserved. # # This code is based on EleutherAI's GPT-NeoX library and the GPT-NeoX diff --git a/vllm/model_executor/models/bart.py b/vllm/model_executor/models/bart.py index 57eb5adc8..204c48d0d 100644 --- a/vllm/model_executor/models/bart.py +++ b/vllm/model_executor/models/bart.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Derived from BART implementation posted on HuggingFace; license below: # # coding=utf-8 diff --git a/vllm/model_executor/models/bert.py b/vllm/model_executor/models/bert.py index 4be136543..4d0f5ac8e 100644 --- a/vllm/model_executor/models/bert.py +++ b/vllm/model_executor/models/bert.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Iterable, List, Optional, Set, Tuple import torch diff --git a/vllm/model_executor/models/blip.py b/vllm/model_executor/models/blip.py index 987dfaf44..bedbdceb7 100644 --- a/vllm/model_executor/models/blip.py +++ b/vllm/model_executor/models/blip.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Minimal implementation of BlipVisionModel intended to be only used within a vision language model.""" from typing import Iterable, Optional, Set, Tuple, Union diff --git a/vllm/model_executor/models/blip2.py b/vllm/model_executor/models/blip2.py index b559ac677..2b0452222 100644 --- a/vllm/model_executor/models/blip2.py +++ b/vllm/model_executor/models/blip2.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from functools import cached_property from typing import (Iterable, List, Literal, Mapping, Optional, Set, Tuple, TypedDict, Union) diff --git a/vllm/model_executor/models/bloom.py b/vllm/model_executor/models/bloom.py index fee74f491..229677ae7 100644 --- a/vllm/model_executor/models/bloom.py +++ b/vllm/model_executor/models/bloom.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Adapted from # https://github.com/huggingface/transformers/blob/v4.28.0/src/transformers/models/bloom/modeling_bloom.py # Copyright 2023 The vLLM team. diff --git a/vllm/model_executor/models/chameleon.py b/vllm/model_executor/models/chameleon.py index e834c9004..9061a3128 100644 --- a/vllm/model_executor/models/chameleon.py +++ b/vllm/model_executor/models/chameleon.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from functools import cached_property from typing import (Any, Dict, Iterable, List, Literal, Mapping, Optional, Set, Tuple, TypedDict, Union) diff --git a/vllm/model_executor/models/chatglm.py b/vllm/model_executor/models/chatglm.py index d5f9b4d19..b81a9e917 100644 --- a/vllm/model_executor/models/chatglm.py +++ b/vllm/model_executor/models/chatglm.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Adapted from # https://github.com/THUDM/CogAgent """Inference-only CogAgent model compatible with THUDM weights.""" diff --git a/vllm/model_executor/models/clip.py b/vllm/model_executor/models/clip.py index dd69f6c9a..1e784f5b4 100644 --- a/vllm/model_executor/models/clip.py +++ b/vllm/model_executor/models/clip.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Minimal implementation of CLIPVisionModel intended to be only used within a vision language model.""" from typing import Iterable, List, Optional, Set, Tuple, Union diff --git a/vllm/model_executor/models/commandr.py b/vllm/model_executor/models/commandr.py index 989056bf5..e73627da0 100644 --- a/vllm/model_executor/models/commandr.py +++ b/vllm/model_executor/models/commandr.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Copyright 2024 Cohere and the HuggingFace Inc. team. All rights reserved. # # This code is based on EleutherAI's GPT-NeoX library and the GPT-NeoX diff --git a/vllm/model_executor/models/dbrx.py b/vllm/model_executor/models/dbrx.py index b2aa3c070..bb3f4f40d 100644 --- a/vllm/model_executor/models/dbrx.py +++ b/vllm/model_executor/models/dbrx.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Iterable, List, Optional, Set, Tuple, Union import torch diff --git a/vllm/model_executor/models/decilm.py b/vllm/model_executor/models/decilm.py index c55185395..b239b642f 100644 --- a/vllm/model_executor/models/decilm.py +++ b/vllm/model_executor/models/decilm.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Adapted from # https://github.com/huggingface/transformers/blob/v4.28.0/src/transformers/models/llama/modeling_llama.py # Copyright 2023 DeciAI Research Team. All rights reserved. diff --git a/vllm/model_executor/models/deepseek.py b/vllm/model_executor/models/deepseek.py index 74b6bfdf2..9599e1df6 100644 --- a/vllm/model_executor/models/deepseek.py +++ b/vllm/model_executor/models/deepseek.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Adapted from # https://github.com/huggingface/transformers/blob/v4.28.0/src/transformers/models/llama/modeling_llama.py # Copyright 2023 The vLLM team. diff --git a/vllm/model_executor/models/deepseek_v2.py b/vllm/model_executor/models/deepseek_v2.py index 73388cd26..f5fede4d8 100644 --- a/vllm/model_executor/models/deepseek_v2.py +++ b/vllm/model_executor/models/deepseek_v2.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Adapted from # https://github.com/huggingface/transformers/blob/v4.28.0/src/transformers/models/llama/modeling_llama.py # Copyright 2023 The vLLM team. diff --git a/vllm/model_executor/models/deepseek_v3.py b/vllm/model_executor/models/deepseek_v3.py index 06ea3dab9..a4829aa1a 100644 --- a/vllm/model_executor/models/deepseek_v3.py +++ b/vllm/model_executor/models/deepseek_v3.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Adapted from # https://github.com/huggingface/transformers/blob/v4.28.0/src/transformers/models/llama/modeling_llama.py # Copyright 2023 The vLLM team. diff --git a/vllm/model_executor/models/deepseek_vl2.py b/vllm/model_executor/models/deepseek_vl2.py index 344832d8b..1343b9762 100644 --- a/vllm/model_executor/models/deepseek_vl2.py +++ b/vllm/model_executor/models/deepseek_vl2.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # adapted from https://github.com/deepseek-ai/DeepSeek-VL2/blob/faf18023f24b962b32d9f0a2d89e402a8d383a78/deepseek_vl2/models/modeling_deepseek_vl_v2.py """Inference-only Deepseek-VL2 model compatible with HuggingFace weights.""" import math diff --git a/vllm/model_executor/models/eagle.py b/vllm/model_executor/models/eagle.py index 948560b49..373a728be 100644 --- a/vllm/model_executor/models/eagle.py +++ b/vllm/model_executor/models/eagle.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Iterable, List, Optional, Tuple import torch diff --git a/vllm/model_executor/models/exaone.py b/vllm/model_executor/models/exaone.py index bc3295da7..2eb91a682 100644 --- a/vllm/model_executor/models/exaone.py +++ b/vllm/model_executor/models/exaone.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Adapted from # https://huggingface.co/LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct/blob/main/modeling_exaone.py # Copyright 2024 The LG U+ CTO AI Tech Lab. diff --git a/vllm/model_executor/models/fairseq2_llama.py b/vllm/model_executor/models/fairseq2_llama.py index b93a68680..310aca999 100644 --- a/vllm/model_executor/models/fairseq2_llama.py +++ b/vllm/model_executor/models/fairseq2_llama.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Copyright 2024 The vLLM team. # Copyright 2024 Meta Platforms, Inc. and affiliates. All rights reserved. # diff --git a/vllm/model_executor/models/falcon.py b/vllm/model_executor/models/falcon.py index c503a368e..01b66a1c2 100644 --- a/vllm/model_executor/models/falcon.py +++ b/vllm/model_executor/models/falcon.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Adapted from # https://github.com/huggingface/transformers/blob/a5cc30d72ae2dc19af534e4b35c986cc28db1275/src/transformers/models/falcon/modeling_falcon.py # Copyright 2023 The vLLM team. diff --git a/vllm/model_executor/models/florence2.py b/vllm/model_executor/models/florence2.py index 3a5fe8e1f..4a1ad5f4e 100644 --- a/vllm/model_executor/models/florence2.py +++ b/vllm/model_executor/models/florence2.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import math from typing import Iterable, List, Optional, Set, Tuple diff --git a/vllm/model_executor/models/fuyu.py b/vllm/model_executor/models/fuyu.py index dbf9da50c..6d8c82968 100644 --- a/vllm/model_executor/models/fuyu.py +++ b/vllm/model_executor/models/fuyu.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # adapted from https://github.com/huggingface/transformers/blob/v4.39.3/src/transformers/models/fuyu/modeling_fuyu.py # Copyright 2023 The vLLM team. # Copyright 2023 HuggingFace Inc. team. All rights reserved. diff --git a/vllm/model_executor/models/gemma.py b/vllm/model_executor/models/gemma.py index b23aba829..cb81aa41e 100644 --- a/vllm/model_executor/models/gemma.py +++ b/vllm/model_executor/models/gemma.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Copyright 2023 The vLLM team. # Copyright (c) Google Inc. # diff --git a/vllm/model_executor/models/gemma2.py b/vllm/model_executor/models/gemma2.py index f0dc76939..a6dc8f847 100644 --- a/vllm/model_executor/models/gemma2.py +++ b/vllm/model_executor/models/gemma2.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Copyright 2024 The vLLM team. # Copyright 2024 Google Inc. HuggingFace Inc. team. All rights reserved. # diff --git a/vllm/model_executor/models/glm.py b/vllm/model_executor/models/glm.py index 942d1e14b..5f1903345 100644 --- a/vllm/model_executor/models/glm.py +++ b/vllm/model_executor/models/glm.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Inference-only HF format GLM-4 model compatible with THUDM weights.""" from vllm.config import VllmConfig from vllm.model_executor.models.llama import LlamaForCausalLM diff --git a/vllm/model_executor/models/glm4_vision_encoder.py b/vllm/model_executor/models/glm4_vision_encoder.py index 51922e6f2..4449eb8e8 100644 --- a/vllm/model_executor/models/glm4_vision_encoder.py +++ b/vllm/model_executor/models/glm4_vision_encoder.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Adapted from # https://github.com/THUDM/GLM-4 """Inference-only GLM-4v model visual encoder compatible with THUDM weights.""" diff --git a/vllm/model_executor/models/gpt2.py b/vllm/model_executor/models/gpt2.py index 2f1aa2d68..7ad9a24dc 100644 --- a/vllm/model_executor/models/gpt2.py +++ b/vllm/model_executor/models/gpt2.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Adapted from # https://github.com/huggingface/transformers/blob/v4.28.0/src/transformers/models/gpt2/modeling_gpt2.py # Copyright 2023 The vLLM team. diff --git a/vllm/model_executor/models/gpt_bigcode.py b/vllm/model_executor/models/gpt_bigcode.py index c64bc7068..887a44474 100644 --- a/vllm/model_executor/models/gpt_bigcode.py +++ b/vllm/model_executor/models/gpt_bigcode.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Adapted from # https://github.com/huggingface/transformers/blob/v4.28.0/src/transformers/models/gpt2/modeling_gpt2.py # Copyright 2023 The vLLM team. diff --git a/vllm/model_executor/models/gpt_j.py b/vllm/model_executor/models/gpt_j.py index 08298cc0d..815aba145 100644 --- a/vllm/model_executor/models/gpt_j.py +++ b/vllm/model_executor/models/gpt_j.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Adapted from # https://github.com/huggingface/transformers/blob/v4.28.0/src/transformers/models/gptj/modeling_gptj.py # Copyright 2023 The vLLM team. diff --git a/vllm/model_executor/models/gpt_neox.py b/vllm/model_executor/models/gpt_neox.py index 731642772..550ca3f7c 100644 --- a/vllm/model_executor/models/gpt_neox.py +++ b/vllm/model_executor/models/gpt_neox.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Adapted from # https://github.com/huggingface/transformers/blob/v4.28.0/src/transformers/models/gpt_neox/modeling_gpt_neox.py # Copyright 2023 The vLLM team. diff --git a/vllm/model_executor/models/granite.py b/vllm/model_executor/models/granite.py index 543b4e2f5..85911a0f4 100644 --- a/vllm/model_executor/models/granite.py +++ b/vllm/model_executor/models/granite.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Adapted from # https://github.com/huggingface/transformers/blob/v4.28.0/src/transformers/models/llama/modeling_llama.py # Copyright 2023 The vLLM team. diff --git a/vllm/model_executor/models/granitemoe.py b/vllm/model_executor/models/granitemoe.py index cdf9414d5..8ae661bf1 100644 --- a/vllm/model_executor/models/granitemoe.py +++ b/vllm/model_executor/models/granitemoe.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Adapted from # https://github.com/huggingface/transformers/blob/v4.28.0/src/transformers/models/llama/modeling_llama.py # Copyright 2023 The vLLM team. diff --git a/vllm/model_executor/models/gritlm.py b/vllm/model_executor/models/gritlm.py index d179d6235..7bda54ea7 100644 --- a/vllm/model_executor/models/gritlm.py +++ b/vllm/model_executor/models/gritlm.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from array import array from typing import List, Optional, Union diff --git a/vllm/model_executor/models/h2ovl.py b/vllm/model_executor/models/h2ovl.py index df7e768fe..91c89b159 100644 --- a/vllm/model_executor/models/h2ovl.py +++ b/vllm/model_executor/models/h2ovl.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # adapted from https://huggingface.co/h2oai/h2ovl-mississippi-2b/blob/main/modeling_h2ovl_chat.py # https://huggingface.co/h2oai/h2ovl-mississippi-2b/blob/main/image_process.py # -------------------------------------------------------- diff --git a/vllm/model_executor/models/idefics2_vision_model.py b/vllm/model_executor/models/idefics2_vision_model.py index 4e42a4b6f..f9c2175b2 100644 --- a/vllm/model_executor/models/idefics2_vision_model.py +++ b/vllm/model_executor/models/idefics2_vision_model.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # adapted from https://github.com/huggingface/transformers/blob/v4.43.2/src/transformers/models/idefics2/modeling_idefics2.py # Copyright 2024 The vLLM team. # Copyright 2024 the HuggingFace Inc. team. All rights reserved. diff --git a/vllm/model_executor/models/idefics3.py b/vllm/model_executor/models/idefics3.py index d16a77f86..9e2e677a6 100644 --- a/vllm/model_executor/models/idefics3.py +++ b/vllm/model_executor/models/idefics3.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Copyright 2024 the HuggingFace Inc. team. All rights reserved. # # Licensed under the Apache License, Version 2.0 (the "License"); diff --git a/vllm/model_executor/models/interfaces.py b/vllm/model_executor/models/interfaces.py index c5fd0d933..0fc5c4db1 100644 --- a/vllm/model_executor/models/interfaces.py +++ b/vllm/model_executor/models/interfaces.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import (TYPE_CHECKING, ClassVar, Dict, List, Literal, Optional, Protocol, Type, Union, overload, runtime_checkable) diff --git a/vllm/model_executor/models/interfaces_base.py b/vllm/model_executor/models/interfaces_base.py index 37b91a803..c5f7be135 100644 --- a/vllm/model_executor/models/interfaces_base.py +++ b/vllm/model_executor/models/interfaces_base.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import (TYPE_CHECKING, List, Optional, Protocol, Type, Union, overload, runtime_checkable) diff --git a/vllm/model_executor/models/intern_vit.py b/vllm/model_executor/models/intern_vit.py index 8ad009d51..0499f339b 100644 --- a/vllm/model_executor/models/intern_vit.py +++ b/vllm/model_executor/models/intern_vit.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # adapted from https://huggingface.co/OpenGVLab/InternVL2-4B/blob/main/modeling_intern_vit.py # -------------------------------------------------------- # InternVL diff --git a/vllm/model_executor/models/internlm2.py b/vllm/model_executor/models/internlm2.py index 28c23edd4..c211ca5f4 100644 --- a/vllm/model_executor/models/internlm2.py +++ b/vllm/model_executor/models/internlm2.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from functools import partial from typing import Any, Dict, Iterable, List, Optional, Set, Tuple, Type, Union diff --git a/vllm/model_executor/models/internlm2_ve.py b/vllm/model_executor/models/internlm2_ve.py index 93ac2dcf8..106c3b6b7 100644 --- a/vllm/model_executor/models/internlm2_ve.py +++ b/vllm/model_executor/models/internlm2_ve.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List, Optional, Tuple, Union import torch diff --git a/vllm/model_executor/models/internvl.py b/vllm/model_executor/models/internvl.py index f4b7e4478..c46a867a7 100644 --- a/vllm/model_executor/models/internvl.py +++ b/vllm/model_executor/models/internvl.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # adapted from https://huggingface.co/OpenGVLab/InternVL2-4B/blob/main/modeling_internvl_chat.py # -------------------------------------------------------- # InternVL diff --git a/vllm/model_executor/models/jais.py b/vllm/model_executor/models/jais.py index 8c81dff6b..72bcef5e2 100644 --- a/vllm/model_executor/models/jais.py +++ b/vllm/model_executor/models/jais.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Adapted from # https://huggingface.co/inceptionai/jais-30b-chat-v3/blob/main/modeling_jais.py # Copyright 2023 The vLLM team. diff --git a/vllm/model_executor/models/jamba.py b/vllm/model_executor/models/jamba.py index 890b5530b..d82c08152 100644 --- a/vllm/model_executor/models/jamba.py +++ b/vllm/model_executor/models/jamba.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Inference-only Jamba model.""" from typing import Iterable, List, Optional, Set, Tuple diff --git a/vllm/model_executor/models/llama.py b/vllm/model_executor/models/llama.py index e7c264c04..d91c8782a 100644 --- a/vllm/model_executor/models/llama.py +++ b/vllm/model_executor/models/llama.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Adapted from # https://github.com/huggingface/transformers/blob/v4.28.0/src/transformers/models/llama/modeling_llama.py # Copyright 2023 The vLLM team. diff --git a/vllm/model_executor/models/llava.py b/vllm/model_executor/models/llava.py index 296af2aac..de3777cad 100644 --- a/vllm/model_executor/models/llava.py +++ b/vllm/model_executor/models/llava.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from abc import abstractmethod from functools import cached_property from typing import (Final, Iterable, List, Literal, Mapping, Optional, diff --git a/vllm/model_executor/models/llava_next.py b/vllm/model_executor/models/llava_next.py index fda4f22d3..185edcb8d 100644 --- a/vllm/model_executor/models/llava_next.py +++ b/vllm/model_executor/models/llava_next.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from abc import abstractmethod from functools import cached_property from typing import (Final, Iterable, List, Literal, Mapping, Optional, diff --git a/vllm/model_executor/models/llava_next_video.py b/vllm/model_executor/models/llava_next_video.py index 5be85d7c0..a50025135 100644 --- a/vllm/model_executor/models/llava_next_video.py +++ b/vllm/model_executor/models/llava_next_video.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import math from functools import cached_property from typing import (Iterable, List, Literal, Mapping, Optional, Set, Tuple, diff --git a/vllm/model_executor/models/llava_onevision.py b/vllm/model_executor/models/llava_onevision.py index 5b0f35b08..ac502000c 100644 --- a/vllm/model_executor/models/llava_onevision.py +++ b/vllm/model_executor/models/llava_onevision.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import math from functools import cached_property from typing import (Final, Iterable, List, Literal, Mapping, Optional, diff --git a/vllm/model_executor/models/mamba.py b/vllm/model_executor/models/mamba.py index 553bc9c28..5034b3345 100644 --- a/vllm/model_executor/models/mamba.py +++ b/vllm/model_executor/models/mamba.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """PyTorch MAMBA model.""" from typing import Iterable, List, Optional, Set, Tuple diff --git a/vllm/model_executor/models/mamba_cache.py b/vllm/model_executor/models/mamba_cache.py index 79393421f..353177f78 100644 --- a/vllm/model_executor/models/mamba_cache.py +++ b/vllm/model_executor/models/mamba_cache.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from dataclasses import dataclass from typing import Dict, List diff --git a/vllm/model_executor/models/medusa.py b/vllm/model_executor/models/medusa.py index 66bdcb89a..a19d7da56 100644 --- a/vllm/model_executor/models/medusa.py +++ b/vllm/model_executor/models/medusa.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Iterable, List, Optional, Set, Tuple import torch diff --git a/vllm/model_executor/models/minicpm.py b/vllm/model_executor/models/minicpm.py index 6254d26c7..29473f5bb 100644 --- a/vllm/model_executor/models/minicpm.py +++ b/vllm/model_executor/models/minicpm.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Adapted from # https://github.com/huggingface/transformers/blob/v4.28.0/src/transformers/models/llama/modeling_llama.py # Copyright 2023 The vLLM team. diff --git a/vllm/model_executor/models/minicpm3.py b/vllm/model_executor/models/minicpm3.py index 5e1e6c6fa..878f0c895 100644 --- a/vllm/model_executor/models/minicpm3.py +++ b/vllm/model_executor/models/minicpm3.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Adapted from # https://github.com/huggingface/transformers/blob/v4.28.0/src/transformers/models/llama/modeling_llama.py # Copyright 2024 The ModelBest team. diff --git a/vllm/model_executor/models/minicpmo.py b/vllm/model_executor/models/minicpmo.py index eb4282d62..f1c168076 100644 --- a/vllm/model_executor/models/minicpmo.py +++ b/vllm/model_executor/models/minicpmo.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Adapted from # https://github.com/huggingface/transformers/blob/v4.28.0/src/transformers/models/llama/modeling_llama.py # Copyright 2023 The vLLM team. diff --git a/vllm/model_executor/models/minicpmv.py b/vllm/model_executor/models/minicpmv.py index bf967d33a..6964d6bdc 100644 --- a/vllm/model_executor/models/minicpmv.py +++ b/vllm/model_executor/models/minicpmv.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Adapted from # https://github.com/huggingface/transformers/blob/v4.28.0/src/transformers/models/llama/modeling_llama.py # Copyright 2023 The vLLM team. diff --git a/vllm/model_executor/models/mixtral.py b/vllm/model_executor/models/mixtral.py index fbb3704fa..70880eb75 100644 --- a/vllm/model_executor/models/mixtral.py +++ b/vllm/model_executor/models/mixtral.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Adapted from # https://github.com/huggingface/transformers/blob/v4.28.0/src/transformers/models/llama/modeling_llama.py # Copyright 2023 The vLLM team. diff --git a/vllm/model_executor/models/mixtral_quant.py b/vllm/model_executor/models/mixtral_quant.py index 7a9b8cd88..fdc438917 100644 --- a/vllm/model_executor/models/mixtral_quant.py +++ b/vllm/model_executor/models/mixtral_quant.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Adapted from # https://github.com/huggingface/transformers/blob/v4.28.0/src/transformers/models/llama/modeling_llama.py # Copyright 2023 The vLLM team. diff --git a/vllm/model_executor/models/mllama.py b/vllm/model_executor/models/mllama.py index f7f9d7a18..d1cb04cdb 100644 --- a/vllm/model_executor/models/mllama.py +++ b/vllm/model_executor/models/mllama.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Copyright 2024 the HuggingFace Inc. team. All rights reserved. # # Licensed under the Apache License, Version 2.0 (the "License"); diff --git a/vllm/model_executor/models/mlp_speculator.py b/vllm/model_executor/models/mlp_speculator.py index f1d796ca2..cf4123a2c 100644 --- a/vllm/model_executor/models/mlp_speculator.py +++ b/vllm/model_executor/models/mlp_speculator.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import math from typing import Iterable, List, Set, Tuple diff --git a/vllm/model_executor/models/module_mapping.py b/vllm/model_executor/models/module_mapping.py index a9102a607..23814e632 100644 --- a/vllm/model_executor/models/module_mapping.py +++ b/vllm/model_executor/models/module_mapping.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Adapted from # https://github.com/modelscope/ms-swift/blob/v2.4.2/swift/utils/module_mapping.py diff --git a/vllm/model_executor/models/molmo.py b/vllm/model_executor/models/molmo.py index 5c7ae0dee..b524a1497 100644 --- a/vllm/model_executor/models/molmo.py +++ b/vllm/model_executor/models/molmo.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import math import re from array import array diff --git a/vllm/model_executor/models/mpt.py b/vllm/model_executor/models/mpt.py index 123581641..676c96062 100644 --- a/vllm/model_executor/models/mpt.py +++ b/vllm/model_executor/models/mpt.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Adapted from https://huggingface.co/mosaicml/mpt-7b/tree/main import math from typing import Iterable, List, Optional, Set, Tuple, Union diff --git a/vllm/model_executor/models/nemotron.py b/vllm/model_executor/models/nemotron.py index 2340283b6..6f0b831ac 100644 --- a/vllm/model_executor/models/nemotron.py +++ b/vllm/model_executor/models/nemotron.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Adapted from # https://github.com/huggingface/transformers/blob/v4.28.0/src/transformers/models/llama/modeling_llama.py # Copyright 2023 The vLLM team. diff --git a/vllm/model_executor/models/nvlm_d.py b/vllm/model_executor/models/nvlm_d.py index df4fd0a32..2aa04bd71 100644 --- a/vllm/model_executor/models/nvlm_d.py +++ b/vllm/model_executor/models/nvlm_d.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # adapted from https://huggingface.co/nvidia/NVLM-D-72B/blob/main/modeling_nvlm_d.py # -------------------------------------------------------- # NVLM-D diff --git a/vllm/model_executor/models/olmo.py b/vllm/model_executor/models/olmo.py index 538e31ec9..3b470dfdd 100644 --- a/vllm/model_executor/models/olmo.py +++ b/vllm/model_executor/models/olmo.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Adapted from # https://github.com/huggingface/transformers/blob/v4.40.1/src/transformers/models/olmo/modeling_olmo.py # Copyright 2024 The vLLM team. diff --git a/vllm/model_executor/models/olmo2.py b/vllm/model_executor/models/olmo2.py index a35c911f9..4b0455098 100644 --- a/vllm/model_executor/models/olmo2.py +++ b/vllm/model_executor/models/olmo2.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Adapted from # https://github.com/huggingface/transformers/blob/main/src/transformers/models/olmo2/modeling_olmo2.py # Copyright 2024 The vLLM team. diff --git a/vllm/model_executor/models/olmoe.py b/vllm/model_executor/models/olmoe.py index fbe5d1aee..d6e24c6d6 100644 --- a/vllm/model_executor/models/olmoe.py +++ b/vllm/model_executor/models/olmoe.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at diff --git a/vllm/model_executor/models/opt.py b/vllm/model_executor/models/opt.py index ea1185aa8..ad1d66902 100644 --- a/vllm/model_executor/models/opt.py +++ b/vllm/model_executor/models/opt.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Adapted from # https://github.com/huggingface/transformers/blob/v4.28.0/src/transformers/models/opt/modeling_opt.py # Copyright 2023 The vLLM team. diff --git a/vllm/model_executor/models/orion.py b/vllm/model_executor/models/orion.py index a3757b5c8..f4f5cdff6 100644 --- a/vllm/model_executor/models/orion.py +++ b/vllm/model_executor/models/orion.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Adapted from # https://huggingface.co/OrionStarAI/Orion-14B-Base/blob/main/modeling_orion.py # Copyright (c) OrionStar Inc. diff --git a/vllm/model_executor/models/paligemma.py b/vllm/model_executor/models/paligemma.py index 5a28b1ffb..65d810dc2 100644 --- a/vllm/model_executor/models/paligemma.py +++ b/vllm/model_executor/models/paligemma.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import (Iterable, List, Literal, Mapping, Optional, Set, Tuple, TypedDict, Union) diff --git a/vllm/model_executor/models/persimmon.py b/vllm/model_executor/models/persimmon.py index 14dd4b5b1..6a80bea34 100644 --- a/vllm/model_executor/models/persimmon.py +++ b/vllm/model_executor/models/persimmon.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # adapted from https://github.com/huggingface/transformers/blob/v4.39.3/src/transformers/models/persimmon/modeling_persimmon.py # Copyright 2023 The vLLM team. # Copyright 2023 EleutherAI and the HuggingFace Inc. team. All rights reserved. diff --git a/vllm/model_executor/models/phi.py b/vllm/model_executor/models/phi.py index 59b7508a3..6b05bfee9 100644 --- a/vllm/model_executor/models/phi.py +++ b/vllm/model_executor/models/phi.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Adapted from # https://huggingface.co/microsoft/phi-1_5/blob/main/modeling_phi.py # Copyright 2023 The vLLM team. diff --git a/vllm/model_executor/models/phi3.py b/vllm/model_executor/models/phi3.py index 34141511e..8f84e0726 100644 --- a/vllm/model_executor/models/phi3.py +++ b/vllm/model_executor/models/phi3.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Adapted from llama.py """Inference-only Phi3 model code inherit from Llama.py""" diff --git a/vllm/model_executor/models/phi3_small.py b/vllm/model_executor/models/phi3_small.py index f47676b93..a8b7e9b2a 100644 --- a/vllm/model_executor/models/phi3_small.py +++ b/vllm/model_executor/models/phi3_small.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import math from typing import Iterable, List, Optional, Set, Tuple, Union diff --git a/vllm/model_executor/models/phi3v.py b/vllm/model_executor/models/phi3v.py index 0fcda81da..f089fa5d2 100644 --- a/vllm/model_executor/models/phi3v.py +++ b/vllm/model_executor/models/phi3v.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Copyright 2024 The vLLM team. # Copyright 2024 Microsoft and the HuggingFace Inc. team. All rights reserved. # diff --git a/vllm/model_executor/models/phimoe.py b/vllm/model_executor/models/phimoe.py index 6367b770a..aa4bb52c4 100644 --- a/vllm/model_executor/models/phimoe.py +++ b/vllm/model_executor/models/phimoe.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Adapted from # https://github.com/huggingface/transformers/blob/v4.28.0/src/transformers/models/llama/modeling_llama.py # Copyright 2023 The vLLM team. diff --git a/vllm/model_executor/models/pixtral.py b/vllm/model_executor/models/pixtral.py index 37b9989e4..003e9c84c 100644 --- a/vllm/model_executor/models/pixtral.py +++ b/vllm/model_executor/models/pixtral.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import math from dataclasses import dataclass, fields from functools import cached_property diff --git a/vllm/model_executor/models/qwen.py b/vllm/model_executor/models/qwen.py index 86a9d3089..d7f6662bc 100644 --- a/vllm/model_executor/models/qwen.py +++ b/vllm/model_executor/models/qwen.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Adapted from # https://huggingface.co/Qwen/Qwen-7B/blob/main/modeling_qwen.py # Copyright (c) Alibaba Cloud. diff --git a/vllm/model_executor/models/qwen2.py b/vllm/model_executor/models/qwen2.py index 82de1c357..e3de6b64f 100644 --- a/vllm/model_executor/models/qwen2.py +++ b/vllm/model_executor/models/qwen2.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Adapted from # https://github.com/huggingface/transformers/blob/v4.28.0/src/transformers/models/qwen2/modeling_qwen2.py # Copyright 2024 The Qwen team. diff --git a/vllm/model_executor/models/qwen2_audio.py b/vllm/model_executor/models/qwen2_audio.py index fc5aed5c9..cf104ab00 100644 --- a/vllm/model_executor/models/qwen2_audio.py +++ b/vllm/model_executor/models/qwen2_audio.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Copyright 2024 The Qwen team. # Copyright 2023 The vLLM team. # Copyright 2022 EleutherAI and the HuggingFace Inc. team. All rights reserved. diff --git a/vllm/model_executor/models/qwen2_moe.py b/vllm/model_executor/models/qwen2_moe.py index 95de6c218..35d9854a5 100644 --- a/vllm/model_executor/models/qwen2_moe.py +++ b/vllm/model_executor/models/qwen2_moe.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Adapted from # https://github.com/huggingface/transformers/blob/v4.28.0/src/transformers/models/qwen2_moe/modeling_qwen2_moe.py # Copyright 2024 The Qwen team. diff --git a/vllm/model_executor/models/qwen2_rm.py b/vllm/model_executor/models/qwen2_rm.py index 593ce4857..00e4159e2 100644 --- a/vllm/model_executor/models/qwen2_rm.py +++ b/vllm/model_executor/models/qwen2_rm.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Adapted from # https://huggingface.co/Qwen/Qwen2.5-Math-RM-72B/blob/main/modeling_qwen2_rm.py # Copyright 2024 The Qwen team. diff --git a/vllm/model_executor/models/qwen2_vl.py b/vllm/model_executor/models/qwen2_vl.py index a2778ee73..189ac41e8 100644 --- a/vllm/model_executor/models/qwen2_vl.py +++ b/vllm/model_executor/models/qwen2_vl.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Adapted from # https://github.com/huggingface/transformers/blob/19e6e80e10118f855137b90740936c0b11ac397f/src/transformers/models/qwen2_vl/modeling_qwen2_vl.py # Copyright 2024 The Qwen team. diff --git a/vllm/model_executor/models/registry.py b/vllm/model_executor/models/registry.py index de05bf2b7..40bbc7d16 100644 --- a/vllm/model_executor/models/registry.py +++ b/vllm/model_executor/models/registry.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """ Whenever you add an architecture to this page, please also update `tests/models/registry.py` with example HuggingFace models for it. diff --git a/vllm/model_executor/models/roberta.py b/vllm/model_executor/models/roberta.py index 5997a7689..742e63a06 100644 --- a/vllm/model_executor/models/roberta.py +++ b/vllm/model_executor/models/roberta.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import itertools from typing import Iterable, List, Optional, Tuple diff --git a/vllm/model_executor/models/siglip.py b/vllm/model_executor/models/siglip.py index 1e5101897..a81462f6f 100644 --- a/vllm/model_executor/models/siglip.py +++ b/vllm/model_executor/models/siglip.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Implementation of SiglipVisionModel intended to be only used within a vision language model.""" diff --git a/vllm/model_executor/models/solar.py b/vllm/model_executor/models/solar.py index e6d919f23..6215ed814 100644 --- a/vllm/model_executor/models/solar.py +++ b/vllm/model_executor/models/solar.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Adapted from # https://github.com/huggingface/transformers/blob/v4.28.0/src/transformers/models/llama/modeling_llama.py # Copyright 2023 The vLLM team. diff --git a/vllm/model_executor/models/stablelm.py b/vllm/model_executor/models/stablelm.py index c9d1af782..a5d443266 100644 --- a/vllm/model_executor/models/stablelm.py +++ b/vllm/model_executor/models/stablelm.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Copyright 2023 Stability AI, EleutherAI, and The HuggingFace Inc. team. # All rights reserved. # diff --git a/vllm/model_executor/models/starcoder2.py b/vllm/model_executor/models/starcoder2.py index 1cd0dedfe..01ea43666 100644 --- a/vllm/model_executor/models/starcoder2.py +++ b/vllm/model_executor/models/starcoder2.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Copyright 2024 BigCode and the HuggingFace Inc. team. All rights reserved. # # This code is based on EleutherAI's GPT-NeoX library and the GPT-NeoX diff --git a/vllm/model_executor/models/telechat2.py b/vllm/model_executor/models/telechat2.py index 02ca7fe08..a38035e37 100644 --- a/vllm/model_executor/models/telechat2.py +++ b/vllm/model_executor/models/telechat2.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Copyright 2023 The vLLM team. # Copyright 2022 EleutherAI and the HuggingFace Inc. team. All rights reserved. # diff --git a/vllm/model_executor/models/ultravox.py b/vllm/model_executor/models/ultravox.py index 605a0ecf4..5e86b15db 100644 --- a/vllm/model_executor/models/ultravox.py +++ b/vllm/model_executor/models/ultravox.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Adapted from https://github.com/fixie-ai/ultravox/blob/ecd58c4041030bae2ad15aa6bcf04ab43199ea02/ultravox/model/ultravox_model.py """PyTorch Ultravox model.""" import math diff --git a/vllm/model_executor/models/utils.py b/vllm/model_executor/models/utils.py index 01a232fdc..fff4be34d 100644 --- a/vllm/model_executor/models/utils.py +++ b/vllm/model_executor/models/utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import itertools from dataclasses import dataclass, field from typing import (Callable, Dict, Iterable, List, Literal, Mapping, Optional, diff --git a/vllm/model_executor/models/vision.py b/vllm/model_executor/models/vision.py index 57166f05c..0d67ee7bb 100644 --- a/vllm/model_executor/models/vision.py +++ b/vllm/model_executor/models/vision.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from abc import ABC, abstractmethod from typing import Final, Generic, Optional, Protocol, TypeVar, Union diff --git a/vllm/model_executor/models/whisper.py b/vllm/model_executor/models/whisper.py index 15e35fa9c..2319c3160 100644 --- a/vllm/model_executor/models/whisper.py +++ b/vllm/model_executor/models/whisper.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import math from typing import (Iterable, List, Mapping, Optional, Set, Tuple, TypedDict, Union) diff --git a/vllm/model_executor/parameter.py b/vllm/model_executor/parameter.py index a9ce8af15..2b1294bf7 100644 --- a/vllm/model_executor/parameter.py +++ b/vllm/model_executor/parameter.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from fractions import Fraction from typing import Callable, Optional, Union diff --git a/vllm/model_executor/pooling_metadata.py b/vllm/model_executor/pooling_metadata.py index b86cafce8..dea8b0e9d 100644 --- a/vllm/model_executor/pooling_metadata.py +++ b/vllm/model_executor/pooling_metadata.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from dataclasses import dataclass from typing import Any, Dict, List, Tuple diff --git a/vllm/model_executor/sampling_metadata.py b/vllm/model_executor/sampling_metadata.py index 61e8881b6..0a580a4e9 100644 --- a/vllm/model_executor/sampling_metadata.py +++ b/vllm/model_executor/sampling_metadata.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from array import array from dataclasses import dataclass from typing import Dict, List, Optional, Tuple diff --git a/vllm/model_executor/utils.py b/vllm/model_executor/utils.py index 6f1cc9d5e..04f922dfd 100644 --- a/vllm/model_executor/utils.py +++ b/vllm/model_executor/utils.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Utils for model executor.""" from typing import Any, Dict, Optional diff --git a/vllm/multimodal/__init__.py b/vllm/multimodal/__init__.py index 1d7f5d57f..741bd1a6a 100644 --- a/vllm/multimodal/__init__.py +++ b/vllm/multimodal/__init__.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from .base import MultiModalPlaceholderMap, MultiModalPlugin from .hasher import MultiModalHashDict, MultiModalHasher from .inputs import (BatchedTensorInputs, ModalityData, MultiModalDataBuiltins, diff --git a/vllm/multimodal/audio.py b/vllm/multimodal/audio.py index de80f22ba..f379ec168 100644 --- a/vllm/multimodal/audio.py +++ b/vllm/multimodal/audio.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import base64 from io import BytesIO from pathlib import Path diff --git a/vllm/multimodal/base.py b/vllm/multimodal/base.py index fd3ec7e0e..c48d07ba3 100644 --- a/vllm/multimodal/base.py +++ b/vllm/multimodal/base.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from abc import ABC, abstractmethod from collections import defaultdict from pathlib import Path diff --git a/vllm/multimodal/hasher.py b/vllm/multimodal/hasher.py index 24aa1ca65..7d277fd67 100644 --- a/vllm/multimodal/hasher.py +++ b/vllm/multimodal/hasher.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import pickle from typing import TYPE_CHECKING, Iterable, Mapping, Optional diff --git a/vllm/multimodal/image.py b/vllm/multimodal/image.py index da13a381c..98ac8057e 100644 --- a/vllm/multimodal/image.py +++ b/vllm/multimodal/image.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import base64 from functools import lru_cache from io import BytesIO diff --git a/vllm/multimodal/inputs.py b/vllm/multimodal/inputs.py index b35184f68..eb52551bb 100644 --- a/vllm/multimodal/inputs.py +++ b/vllm/multimodal/inputs.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from abc import ABC, abstractmethod from collections import UserDict, defaultdict from collections.abc import Mapping, Sequence diff --git a/vllm/multimodal/parse.py b/vllm/multimodal/parse.py index ccff0e857..063f458b2 100644 --- a/vllm/multimodal/parse.py +++ b/vllm/multimodal/parse.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from abc import ABC, abstractmethod from collections import UserDict from collections.abc import Callable, Iterator, Mapping, Sequence diff --git a/vllm/multimodal/processing.py b/vllm/multimodal/processing.py index 750646ac6..2ad42d1c1 100644 --- a/vllm/multimodal/processing.py +++ b/vllm/multimodal/processing.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import re from abc import ABC, abstractmethod from collections import defaultdict diff --git a/vllm/multimodal/profiling.py b/vllm/multimodal/profiling.py index c68edaff8..953c01000 100644 --- a/vllm/multimodal/profiling.py +++ b/vllm/multimodal/profiling.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from abc import ABC, abstractmethod from collections.abc import Mapping from dataclasses import dataclass, field diff --git a/vllm/multimodal/registry.py b/vllm/multimodal/registry.py index 7a4b85385..29036691b 100644 --- a/vllm/multimodal/registry.py +++ b/vllm/multimodal/registry.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import functools from collections import UserDict from dataclasses import dataclass diff --git a/vllm/multimodal/utils.py b/vllm/multimodal/utils.py index 900bed592..583f53655 100644 --- a/vllm/multimodal/utils.py +++ b/vllm/multimodal/utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from functools import lru_cache from itertools import groupby from pathlib import Path diff --git a/vllm/multimodal/video.py b/vllm/multimodal/video.py index 1ad1f5abc..88f184399 100644 --- a/vllm/multimodal/video.py +++ b/vllm/multimodal/video.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import base64 from functools import lru_cache, partial from io import BytesIO diff --git a/vllm/outputs.py b/vllm/outputs.py index 25b226528..786380c37 100644 --- a/vllm/outputs.py +++ b/vllm/outputs.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import time from dataclasses import dataclass from typing import Dict, Generic, List, MutableSequence, Optional diff --git a/vllm/platforms/__init__.py b/vllm/platforms/__init__.py index ddbdc43ca..d34b660df 100644 --- a/vllm/platforms/__init__.py +++ b/vllm/platforms/__init__.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import logging import traceback from itertools import chain diff --git a/vllm/platforms/cpu.py b/vllm/platforms/cpu.py index 159ea94f9..4e0683b8a 100644 --- a/vllm/platforms/cpu.py +++ b/vllm/platforms/cpu.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import os from typing import TYPE_CHECKING, Optional diff --git a/vllm/platforms/cuda.py b/vllm/platforms/cuda.py index 91dcdff00..44d2506f0 100644 --- a/vllm/platforms/cuda.py +++ b/vllm/platforms/cuda.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Code inside this file can safely assume cuda platform, e.g. importing pynvml. However, it should not initialize cuda context. """ diff --git a/vllm/platforms/hpu.py b/vllm/platforms/hpu.py index 0e1c4c0c5..78ddb67bb 100644 --- a/vllm/platforms/hpu.py +++ b/vllm/platforms/hpu.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import os from typing import TYPE_CHECKING, Optional diff --git a/vllm/platforms/interface.py b/vllm/platforms/interface.py index 186fa54bf..dc6545c93 100644 --- a/vllm/platforms/interface.py +++ b/vllm/platforms/interface.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import enum import platform import random diff --git a/vllm/platforms/neuron.py b/vllm/platforms/neuron.py index 23a7126fb..5a03f5f7a 100644 --- a/vllm/platforms/neuron.py +++ b/vllm/platforms/neuron.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import TYPE_CHECKING, Optional from vllm.logger import init_logger diff --git a/vllm/platforms/openvino.py b/vllm/platforms/openvino.py index 3282c0617..41221de0a 100644 --- a/vllm/platforms/openvino.py +++ b/vllm/platforms/openvino.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import TYPE_CHECKING, Optional import torch diff --git a/vllm/platforms/rocm.py b/vllm/platforms/rocm.py index 888852163..cd851c0d8 100644 --- a/vllm/platforms/rocm.py +++ b/vllm/platforms/rocm.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import os from functools import lru_cache from typing import TYPE_CHECKING, Dict, List, Optional diff --git a/vllm/platforms/tpu.py b/vllm/platforms/tpu.py index 494a17633..fffc61bba 100644 --- a/vllm/platforms/tpu.py +++ b/vllm/platforms/tpu.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import TYPE_CHECKING, Optional import torch diff --git a/vllm/platforms/xpu.py b/vllm/platforms/xpu.py index 039cdd5ad..81bc85f94 100644 --- a/vllm/platforms/xpu.py +++ b/vllm/platforms/xpu.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import TYPE_CHECKING, Optional import torch diff --git a/vllm/plugins/__init__.py b/vllm/plugins/__init__.py index a78a05491..389cb8728 100644 --- a/vllm/plugins/__init__.py +++ b/vllm/plugins/__init__.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import logging import os from typing import Callable, Dict diff --git a/vllm/pooling_params.py b/vllm/pooling_params.py index b24b7e91a..061232eb1 100644 --- a/vllm/pooling_params.py +++ b/vllm/pooling_params.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Any, Optional import msgspec diff --git a/vllm/profiler/__init__.py b/vllm/profiler/__init__.py index 3e25f5cc2..00af72b1d 100644 --- a/vllm/profiler/__init__.py +++ b/vllm/profiler/__init__.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from .layerwise_profile import layerwise_profile __all__ = [ diff --git a/vllm/profiler/layerwise_profile.py b/vllm/profiler/layerwise_profile.py index 29c0edd0e..6351ef63d 100644 --- a/vllm/profiler/layerwise_profile.py +++ b/vllm/profiler/layerwise_profile.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import copy from collections import defaultdict from dataclasses import asdict, dataclass, field diff --git a/vllm/profiler/utils.py b/vllm/profiler/utils.py index 033035e43..62b39f510 100644 --- a/vllm/profiler/utils.py +++ b/vllm/profiler/utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import dataclasses from typing import Callable, Dict, List, Type, Union diff --git a/vllm/prompt_adapter/layers.py b/vllm/prompt_adapter/layers.py index 27a61e692..c2f9f1691 100644 --- a/vllm/prompt_adapter/layers.py +++ b/vllm/prompt_adapter/layers.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from dataclasses import dataclass from typing import Optional diff --git a/vllm/prompt_adapter/models.py b/vllm/prompt_adapter/models.py index 18a5f86c3..3ba7d0896 100644 --- a/vllm/prompt_adapter/models.py +++ b/vllm/prompt_adapter/models.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import logging import math from typing import Any, Callable, Dict, List, Optional, Type diff --git a/vllm/prompt_adapter/request.py b/vllm/prompt_adapter/request.py index 775dd11db..dfb8e61d7 100644 --- a/vllm/prompt_adapter/request.py +++ b/vllm/prompt_adapter/request.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import msgspec from vllm.adapter_commons.request import AdapterRequest diff --git a/vllm/prompt_adapter/utils.py b/vllm/prompt_adapter/utils.py index 8b2732923..dd179ab93 100644 --- a/vllm/prompt_adapter/utils.py +++ b/vllm/prompt_adapter/utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # code borrowed from: https://github.com/huggingface/peft/blob/v0.12.0/src/peft/utils/save_and_load.py#L420 import os diff --git a/vllm/prompt_adapter/worker_manager.py b/vllm/prompt_adapter/worker_manager.py index ddc1ef893..28dcc1687 100644 --- a/vllm/prompt_adapter/worker_manager.py +++ b/vllm/prompt_adapter/worker_manager.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import logging from typing import Any, Optional, Set, Type diff --git a/vllm/sampling_params.py b/vllm/sampling_params.py index 605c09b8d..97f9e2129 100644 --- a/vllm/sampling_params.py +++ b/vllm/sampling_params.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Sampling parameters for text generation.""" import copy from dataclasses import dataclass diff --git a/vllm/scalar_type.py b/vllm/scalar_type.py index 20063a5b4..9f6e85920 100644 --- a/vllm/scalar_type.py +++ b/vllm/scalar_type.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import functools import struct from dataclasses import dataclass diff --git a/vllm/scripts.py b/vllm/scripts.py index 8101e6b3a..467cab28f 100644 --- a/vllm/scripts.py +++ b/vllm/scripts.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # The CLI entrypoint to vLLM. import argparse import os diff --git a/vllm/sequence.py b/vllm/sequence.py index 74320db70..534b9e606 100644 --- a/vllm/sequence.py +++ b/vllm/sequence.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Sequence and its related classes.""" import copy import enum diff --git a/vllm/spec_decode/batch_expansion.py b/vllm/spec_decode/batch_expansion.py index 56fb9ba50..e08ed742a 100644 --- a/vllm/spec_decode/batch_expansion.py +++ b/vllm/spec_decode/batch_expansion.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from array import array from itertools import chain, count from typing import Iterator, List, Optional, Tuple diff --git a/vllm/spec_decode/draft_model_runner.py b/vllm/spec_decode/draft_model_runner.py index fe5fd39f4..3948298db 100644 --- a/vllm/spec_decode/draft_model_runner.py +++ b/vllm/spec_decode/draft_model_runner.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List, Optional import torch diff --git a/vllm/spec_decode/interfaces.py b/vllm/spec_decode/interfaces.py index c39e98b6c..dd085ad77 100644 --- a/vllm/spec_decode/interfaces.py +++ b/vllm/spec_decode/interfaces.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from abc import ABC, abstractmethod from dataclasses import dataclass from typing import List, Optional, Set, Union diff --git a/vllm/spec_decode/medusa_worker.py b/vllm/spec_decode/medusa_worker.py index 21a58fc42..0b62a988e 100644 --- a/vllm/spec_decode/medusa_worker.py +++ b/vllm/spec_decode/medusa_worker.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import weakref from typing import List, Optional, Set, Tuple diff --git a/vllm/spec_decode/metrics.py b/vllm/spec_decode/metrics.py index d678f4578..bc0e0a121 100644 --- a/vllm/spec_decode/metrics.py +++ b/vllm/spec_decode/metrics.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import time from typing import Callable, Optional, Union diff --git a/vllm/spec_decode/mlp_speculator_worker.py b/vllm/spec_decode/mlp_speculator_worker.py index fc41bb82e..bdaf31895 100644 --- a/vllm/spec_decode/mlp_speculator_worker.py +++ b/vllm/spec_decode/mlp_speculator_worker.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List, Optional, Set, Tuple import torch diff --git a/vllm/spec_decode/mqa_scorer.py b/vllm/spec_decode/mqa_scorer.py index 3aea2eabb..6275c460e 100644 --- a/vllm/spec_decode/mqa_scorer.py +++ b/vllm/spec_decode/mqa_scorer.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from vllm.sequence import (ExecuteModelRequest, SequenceData, SequenceGroupMetadata, get_all_seq_ids) from vllm.spec_decode.interfaces import (SpeculativeProposals, diff --git a/vllm/spec_decode/multi_step_worker.py b/vllm/spec_decode/multi_step_worker.py index 32197f8cc..5474917a6 100644 --- a/vllm/spec_decode/multi_step_worker.py +++ b/vllm/spec_decode/multi_step_worker.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import copy import weakref from typing import Dict, List, Set, Tuple diff --git a/vllm/spec_decode/ngram_worker.py b/vllm/spec_decode/ngram_worker.py index e906b1789..86390c99c 100644 --- a/vllm/spec_decode/ngram_worker.py +++ b/vllm/spec_decode/ngram_worker.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import weakref from typing import List, Optional, Set, Tuple diff --git a/vllm/spec_decode/proposer_worker_base.py b/vllm/spec_decode/proposer_worker_base.py index 28a537593..2bebf80fa 100644 --- a/vllm/spec_decode/proposer_worker_base.py +++ b/vllm/spec_decode/proposer_worker_base.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from abc import ABC, abstractmethod from typing import List, Optional, Set, Tuple diff --git a/vllm/spec_decode/smaller_tp_proposer_worker.py b/vllm/spec_decode/smaller_tp_proposer_worker.py index c6ff5e52f..a1466ba5d 100644 --- a/vllm/spec_decode/smaller_tp_proposer_worker.py +++ b/vllm/spec_decode/smaller_tp_proposer_worker.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List, Optional, Set, Tuple import torch diff --git a/vllm/spec_decode/spec_decode_worker.py b/vllm/spec_decode/spec_decode_worker.py index 8d6d05cba..8653bece8 100644 --- a/vllm/spec_decode/spec_decode_worker.py +++ b/vllm/spec_decode/spec_decode_worker.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import copy from collections import defaultdict from functools import cached_property diff --git a/vllm/spec_decode/target_model_runner.py b/vllm/spec_decode/target_model_runner.py index 56540744b..08e773c56 100644 --- a/vllm/spec_decode/target_model_runner.py +++ b/vllm/spec_decode/target_model_runner.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List, Optional from vllm.sequence import SequenceGroupMetadata diff --git a/vllm/spec_decode/top1_proposer.py b/vllm/spec_decode/top1_proposer.py index 6bf7587cd..b538923c0 100644 --- a/vllm/spec_decode/top1_proposer.py +++ b/vllm/spec_decode/top1_proposer.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List, Optional, Set, Tuple import torch diff --git a/vllm/spec_decode/util.py b/vllm/spec_decode/util.py index c88820ab2..9c04680a6 100644 --- a/vllm/spec_decode/util.py +++ b/vllm/spec_decode/util.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import time from contextlib import contextmanager from typing import Dict, List, Optional, Sequence, Tuple diff --git a/vllm/tracing.py b/vllm/tracing.py index 72a3f8511..bf069ad84 100644 --- a/vllm/tracing.py +++ b/vllm/tracing.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import os from typing import Mapping, Optional diff --git a/vllm/transformers_utils/__init__.py b/vllm/transformers_utils/__init__.py index eeec029fc..01d5bb4b5 100644 --- a/vllm/transformers_utils/__init__.py +++ b/vllm/transformers_utils/__init__.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from vllm.envs import VLLM_USE_MODELSCOPE if VLLM_USE_MODELSCOPE: diff --git a/vllm/transformers_utils/config.py b/vllm/transformers_utils/config.py index 5805f4ad0..1c0f20a6e 100644 --- a/vllm/transformers_utils/config.py +++ b/vllm/transformers_utils/config.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import enum import json import os diff --git a/vllm/transformers_utils/configs/__init__.py b/vllm/transformers_utils/configs/__init__.py index f065c5612..c484a755a 100644 --- a/vllm/transformers_utils/configs/__init__.py +++ b/vllm/transformers_utils/configs/__init__.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from vllm.transformers_utils.configs.chatglm import ChatGLMConfig from vllm.transformers_utils.configs.cohere2 import Cohere2Config from vllm.transformers_utils.configs.dbrx import DbrxConfig diff --git a/vllm/transformers_utils/configs/arctic.py b/vllm/transformers_utils/configs/arctic.py index 7780bf5e7..6625ccf0f 100644 --- a/vllm/transformers_utils/configs/arctic.py +++ b/vllm/transformers_utils/configs/arctic.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # yapf: disable # ruff: noqa: E501 # coding=utf-8 diff --git a/vllm/transformers_utils/configs/chatglm.py b/vllm/transformers_utils/configs/chatglm.py index e563bf626..43e9503ff 100644 --- a/vllm/transformers_utils/configs/chatglm.py +++ b/vllm/transformers_utils/configs/chatglm.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Adapted from # https://github.com/THUDM/ChatGLM2-6B from transformers import PretrainedConfig diff --git a/vllm/transformers_utils/configs/cohere2.py b/vllm/transformers_utils/configs/cohere2.py index 1509330fc..e30409b3a 100644 --- a/vllm/transformers_utils/configs/cohere2.py +++ b/vllm/transformers_utils/configs/cohere2.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # ruff: noqa # Adapted from diff --git a/vllm/transformers_utils/configs/dbrx.py b/vllm/transformers_utils/configs/dbrx.py index 0dc966472..8f40b2b7d 100644 --- a/vllm/transformers_utils/configs/dbrx.py +++ b/vllm/transformers_utils/configs/dbrx.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # yapf: disable # ruff: noqa: E501 # coding=utf-8 diff --git a/vllm/transformers_utils/configs/deepseek_vl2.py b/vllm/transformers_utils/configs/deepseek_vl2.py index 681528c3c..24d4052d8 100644 --- a/vllm/transformers_utils/configs/deepseek_vl2.py +++ b/vllm/transformers_utils/configs/deepseek_vl2.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # adapted from https://github.com/deepseek-ai/DeepSeek-VL2/blob/faf18023f24b962b32d9f0a2d89e402a8d383a78/deepseek_vl2/models/modeling_deepseek_vl_v2.py#L115-L268 from typing import Tuple diff --git a/vllm/transformers_utils/configs/eagle.py b/vllm/transformers_utils/configs/eagle.py index b357a785e..b26aba666 100644 --- a/vllm/transformers_utils/configs/eagle.py +++ b/vllm/transformers_utils/configs/eagle.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import os from typing import Optional, Union diff --git a/vllm/transformers_utils/configs/exaone.py b/vllm/transformers_utils/configs/exaone.py index f60a59f55..39364367e 100644 --- a/vllm/transformers_utils/configs/exaone.py +++ b/vllm/transformers_utils/configs/exaone.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Copied from # https://huggingface.co/LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct/blob/main/configuration_exaone.py # Copyright 2021 The LG AI Research EXAONE Lab. All rights reserved. diff --git a/vllm/transformers_utils/configs/falcon.py b/vllm/transformers_utils/configs/falcon.py index c82cc6065..f161a06f3 100644 --- a/vllm/transformers_utils/configs/falcon.py +++ b/vllm/transformers_utils/configs/falcon.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Adapted from # https://huggingface.co/tiiuae/falcon-7b/blob/main/configuration_RW.py # Copyright 2023 The vLLM team. diff --git a/vllm/transformers_utils/configs/h2ovl.py b/vllm/transformers_utils/configs/h2ovl.py index b94c5b77e..48b5d79ff 100644 --- a/vllm/transformers_utils/configs/h2ovl.py +++ b/vllm/transformers_utils/configs/h2ovl.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Adapted from # https://huggingface.co/h2oai/h2ovl-mississippi-2b/blob/main/configuration_h2ovl_chat.py # -------------------------------------------------------- diff --git a/vllm/transformers_utils/configs/internvl.py b/vllm/transformers_utils/configs/internvl.py index ac2492317..8ea62546e 100644 --- a/vllm/transformers_utils/configs/internvl.py +++ b/vllm/transformers_utils/configs/internvl.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Adapted from # https://huggingface.co/OpenGVLab/InternVL2-1B/blob/main/configuration_internvl_chat.py # -------------------------------------------------------- diff --git a/vllm/transformers_utils/configs/jais.py b/vllm/transformers_utils/configs/jais.py index 82f129eb2..0cab2c42e 100644 --- a/vllm/transformers_utils/configs/jais.py +++ b/vllm/transformers_utils/configs/jais.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Copyright 2023 The OpenAI Team Authors and HuggingFace Inc. team. # Copyright (c) 2018, NVIDIA CORPORATION. All rights reserved. # Copyright 2023 Cerebras Systems. diff --git a/vllm/transformers_utils/configs/medusa.py b/vllm/transformers_utils/configs/medusa.py index d71a08343..885713c5d 100644 --- a/vllm/transformers_utils/configs/medusa.py +++ b/vllm/transformers_utils/configs/medusa.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import os from typing import Optional, Union diff --git a/vllm/transformers_utils/configs/mllama.py b/vllm/transformers_utils/configs/mllama.py index 49e766d7f..eb77e09ad 100644 --- a/vllm/transformers_utils/configs/mllama.py +++ b/vllm/transformers_utils/configs/mllama.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from transformers.models.mllama import configuration_mllama as mllama_hf_config diff --git a/vllm/transformers_utils/configs/mlp_speculator.py b/vllm/transformers_utils/configs/mlp_speculator.py index 946af4e91..c761f659e 100644 --- a/vllm/transformers_utils/configs/mlp_speculator.py +++ b/vllm/transformers_utils/configs/mlp_speculator.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List, Optional from transformers import PretrainedConfig diff --git a/vllm/transformers_utils/configs/mpt.py b/vllm/transformers_utils/configs/mpt.py index 0f047c8b0..96356135f 100644 --- a/vllm/transformers_utils/configs/mpt.py +++ b/vllm/transformers_utils/configs/mpt.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Copied from # https://huggingface.co/mosaicml/mpt-7b/blob/main/configuration_mpt.py """A HuggingFace-style model configuration.""" diff --git a/vllm/transformers_utils/configs/nemotron.py b/vllm/transformers_utils/configs/nemotron.py index 1edf36329..fdf4fa2a5 100644 --- a/vllm/transformers_utils/configs/nemotron.py +++ b/vllm/transformers_utils/configs/nemotron.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Copyright 2024 HuggingFace Inc. team. All rights reserved. # Copyright (c) 2024, NVIDIA CORPORATION. All rights reserved. # diff --git a/vllm/transformers_utils/configs/nvlm_d.py b/vllm/transformers_utils/configs/nvlm_d.py index 8007176ae..300f6e211 100644 --- a/vllm/transformers_utils/configs/nvlm_d.py +++ b/vllm/transformers_utils/configs/nvlm_d.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Adapted from # https://huggingface.co/nvidia/NVLM-D-72B/blob/main/configuration_nvlm_d.py # -------------------------------------------------------- diff --git a/vllm/transformers_utils/configs/olmo2.py b/vllm/transformers_utils/configs/olmo2.py index 0e6d8e487..c6e446333 100644 --- a/vllm/transformers_utils/configs/olmo2.py +++ b/vllm/transformers_utils/configs/olmo2.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # yapf: disable # ruff: noqa: E501 # coding=utf-8 diff --git a/vllm/transformers_utils/configs/solar.py b/vllm/transformers_utils/configs/solar.py index 0c1c048f6..0d5db896b 100644 --- a/vllm/transformers_utils/configs/solar.py +++ b/vllm/transformers_utils/configs/solar.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Copyright 2022 EleutherAI and the HuggingFace Inc. team. All rights reserved. # # This code is based on EleutherAI's GPT-NeoX library and the GPT-NeoX diff --git a/vllm/transformers_utils/configs/telechat2.py b/vllm/transformers_utils/configs/telechat2.py index eb6f5a059..5da6c5b44 100644 --- a/vllm/transformers_utils/configs/telechat2.py +++ b/vllm/transformers_utils/configs/telechat2.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # adapted from https://www.modelscope.cn/models/TeleAI/TeleChat2-3B/resolve/master/configuration_telechat2.py """ Telechat configuration compatible with LlamaConfig. """ diff --git a/vllm/transformers_utils/configs/ultravox.py b/vllm/transformers_utils/configs/ultravox.py index f724bf7f2..99715ba6d 100644 --- a/vllm/transformers_utils/configs/ultravox.py +++ b/vllm/transformers_utils/configs/ultravox.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Adapted from https://github.com/fixie-ai/ultravox/blob/ecd58c4041030bae2ad15aa6bcf04ab43199ea02/ultravox/model/ultravox_config.py from typing import Any, Dict, Optional diff --git a/vllm/transformers_utils/detokenizer.py b/vllm/transformers_utils/detokenizer.py index 7c8423d2b..9d1d4bb92 100644 --- a/vllm/transformers_utils/detokenizer.py +++ b/vllm/transformers_utils/detokenizer.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Dict, List, Optional from vllm.sequence import (VLLM_INVALID_TOKEN_ID, Logprob, SamplingParams, diff --git a/vllm/transformers_utils/detokenizer_utils.py b/vllm/transformers_utils/detokenizer_utils.py index 37ff8a236..8160a35ff 100644 --- a/vllm/transformers_utils/detokenizer_utils.py +++ b/vllm/transformers_utils/detokenizer_utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List, Optional, Tuple from .tokenizer import AnyTokenizer diff --git a/vllm/transformers_utils/processor.py b/vllm/transformers_utils/processor.py index b12cc83a2..3197b07d8 100644 --- a/vllm/transformers_utils/processor.py +++ b/vllm/transformers_utils/processor.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from functools import lru_cache from typing import Any, cast diff --git a/vllm/transformers_utils/processors/__init__.py b/vllm/transformers_utils/processors/__init__.py index 9c71b8cad..4696f0c49 100644 --- a/vllm/transformers_utils/processors/__init__.py +++ b/vllm/transformers_utils/processors/__init__.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from vllm.transformers_utils.processors.deepseek_vl2 import ( DeepseekVLV2Processor) diff --git a/vllm/transformers_utils/processors/deepseek_vl2.py b/vllm/transformers_utils/processors/deepseek_vl2.py index 27cdf6bc2..d37381ea9 100644 --- a/vllm/transformers_utils/processors/deepseek_vl2.py +++ b/vllm/transformers_utils/processors/deepseek_vl2.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # yapf: disable # ruff: noqa: E501 # coding=utf-8 diff --git a/vllm/transformers_utils/s3_utils.py b/vllm/transformers_utils/s3_utils.py index 74a56cbf5..4fe744d28 100644 --- a/vllm/transformers_utils/s3_utils.py +++ b/vllm/transformers_utils/s3_utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import fnmatch import os import shutil diff --git a/vllm/transformers_utils/tokenizer.py b/vllm/transformers_utils/tokenizer.py index 1f1d67fab..520870b56 100644 --- a/vllm/transformers_utils/tokenizer.py +++ b/vllm/transformers_utils/tokenizer.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import contextlib import os import warnings diff --git a/vllm/transformers_utils/tokenizer_group/__init__.py b/vllm/transformers_utils/tokenizer_group/__init__.py index 09569c564..c223768b1 100644 --- a/vllm/transformers_utils/tokenizer_group/__init__.py +++ b/vllm/transformers_utils/tokenizer_group/__init__.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Optional, Type from vllm.config import (LoRAConfig, ModelConfig, ParallelConfig, diff --git a/vllm/transformers_utils/tokenizer_group/base_tokenizer_group.py b/vllm/transformers_utils/tokenizer_group/base_tokenizer_group.py index e6cc7cd4e..fbdfa3e57 100644 --- a/vllm/transformers_utils/tokenizer_group/base_tokenizer_group.py +++ b/vllm/transformers_utils/tokenizer_group/base_tokenizer_group.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from abc import ABC, abstractmethod from typing import List, Optional diff --git a/vllm/transformers_utils/tokenizer_group/ray_tokenizer_group.py b/vllm/transformers_utils/tokenizer_group/ray_tokenizer_group.py index 3f7627e11..30cab752c 100644 --- a/vllm/transformers_utils/tokenizer_group/ray_tokenizer_group.py +++ b/vllm/transformers_utils/tokenizer_group/ray_tokenizer_group.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import asyncio import os from typing import List, Optional diff --git a/vllm/transformers_utils/tokenizer_group/tokenizer_group.py b/vllm/transformers_utils/tokenizer_group/tokenizer_group.py index 6dc2f9056..025971cb7 100644 --- a/vllm/transformers_utils/tokenizer_group/tokenizer_group.py +++ b/vllm/transformers_utils/tokenizer_group/tokenizer_group.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List, Optional from vllm.config import TokenizerPoolConfig diff --git a/vllm/transformers_utils/tokenizers/__init__.py b/vllm/transformers_utils/tokenizers/__init__.py index e68ad79b2..2b64f3fc7 100644 --- a/vllm/transformers_utils/tokenizers/__init__.py +++ b/vllm/transformers_utils/tokenizers/__init__.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from .mistral import MistralTokenizer, maybe_serialize_tool_calls __all__ = ["MistralTokenizer", "maybe_serialize_tool_calls"] diff --git a/vllm/transformers_utils/tokenizers/mistral.py b/vllm/transformers_utils/tokenizers/mistral.py index d801cf4e4..cecafcc78 100644 --- a/vllm/transformers_utils/tokenizers/mistral.py +++ b/vllm/transformers_utils/tokenizers/mistral.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import os import re from dataclasses import dataclass diff --git a/vllm/transformers_utils/utils.py b/vllm/transformers_utils/utils.py index 10a09fb4f..71fe3ef0b 100644 --- a/vllm/transformers_utils/utils.py +++ b/vllm/transformers_utils/utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from os import PathLike from pathlib import Path from typing import Union diff --git a/vllm/triton_utils/__init__.py b/vllm/triton_utils/__init__.py index 568185383..c8f7a32ce 100644 --- a/vllm/triton_utils/__init__.py +++ b/vllm/triton_utils/__init__.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from vllm.triton_utils.importing import HAS_TRITON __all__ = ["HAS_TRITON"] diff --git a/vllm/triton_utils/custom_cache_manager.py b/vllm/triton_utils/custom_cache_manager.py index 17039d7ba..4163969c9 100644 --- a/vllm/triton_utils/custom_cache_manager.py +++ b/vllm/triton_utils/custom_cache_manager.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import os from triton.runtime.cache import (FileCacheManager, default_cache_dir, diff --git a/vllm/triton_utils/importing.py b/vllm/triton_utils/importing.py index 0c96e0632..a20700248 100644 --- a/vllm/triton_utils/importing.py +++ b/vllm/triton_utils/importing.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from importlib.util import find_spec from vllm.logger import init_logger diff --git a/vllm/usage/usage_lib.py b/vllm/usage/usage_lib.py index 7f5cc9063..fbbb21c89 100644 --- a/vllm/usage/usage_lib.py +++ b/vllm/usage/usage_lib.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import datetime import json import logging diff --git a/vllm/utils.py b/vllm/utils.py index 15481fb06..3089f0951 100644 --- a/vllm/utils.py +++ b/vllm/utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import argparse import asyncio import concurrent diff --git a/vllm/v1/attention/backends/flash_attn.py b/vllm/v1/attention/backends/flash_attn.py index ce83b1fac..837d7faf4 100755 --- a/vllm/v1/attention/backends/flash_attn.py +++ b/vllm/v1/attention/backends/flash_attn.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """Attention layer with FlashAttention.""" from dataclasses import dataclass from typing import Any, Dict, List, Optional, Tuple, Type diff --git a/vllm/v1/core/encoder_cache_manager.py b/vllm/v1/core/encoder_cache_manager.py index 9d570b334..651bc01aa 100644 --- a/vllm/v1/core/encoder_cache_manager.py +++ b/vllm/v1/core/encoder_cache_manager.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import TYPE_CHECKING, Dict, List, Set, Tuple from vllm.logger import init_logger diff --git a/vllm/v1/core/kv_cache_manager.py b/vllm/v1/core/kv_cache_manager.py index 7176ec954..94086e4a1 100644 --- a/vllm/v1/core/kv_cache_manager.py +++ b/vllm/v1/core/kv_cache_manager.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from collections import defaultdict from typing import DefaultDict, Dict, Iterable, List, Optional, Tuple diff --git a/vllm/v1/core/kv_cache_utils.py b/vllm/v1/core/kv_cache_utils.py index 2b6557ad3..c801ab9e4 100644 --- a/vllm/v1/core/kv_cache_utils.py +++ b/vllm/v1/core/kv_cache_utils.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """KV-Cache Utilities.""" from collections.abc import Sequence from dataclasses import dataclass diff --git a/vllm/v1/core/scheduler.py b/vllm/v1/core/scheduler.py index 27c9ac1ae..f4738bb33 100644 --- a/vllm/v1/core/scheduler.py +++ b/vllm/v1/core/scheduler.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from collections import deque from dataclasses import dataclass from typing import (TYPE_CHECKING, Deque, Dict, Iterable, List, Optional, Set, diff --git a/vllm/v1/engine/__init__.py b/vllm/v1/engine/__init__.py index abe4952c4..912b92862 100644 --- a/vllm/v1/engine/__init__.py +++ b/vllm/v1/engine/__init__.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import enum from dataclasses import dataclass from typing import TYPE_CHECKING, List, Optional, Union diff --git a/vllm/v1/engine/async_llm.py b/vllm/v1/engine/async_llm.py index b9dc3561d..3c4e35e4a 100644 --- a/vllm/v1/engine/async_llm.py +++ b/vllm/v1/engine/async_llm.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import asyncio import os from typing import AsyncGenerator, List, Mapping, Optional, Type, Union diff --git a/vllm/v1/engine/core.py b/vllm/v1/engine/core.py index f50303bda..29a9ac186 100644 --- a/vllm/v1/engine/core.py +++ b/vllm/v1/engine/core.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import pickle import queue import signal diff --git a/vllm/v1/engine/core_client.py b/vllm/v1/engine/core_client.py index f3b992d68..247380ef7 100644 --- a/vllm/v1/engine/core_client.py +++ b/vllm/v1/engine/core_client.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import asyncio import os import signal diff --git a/vllm/v1/engine/detokenizer.py b/vllm/v1/engine/detokenizer.py index 4a8b61bee..6d800f026 100644 --- a/vllm/v1/engine/detokenizer.py +++ b/vllm/v1/engine/detokenizer.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from dataclasses import dataclass from typing import List, Optional, Union diff --git a/vllm/v1/engine/llm_engine.py b/vllm/v1/engine/llm_engine.py index 55d314ebe..e0452bcad 100644 --- a/vllm/v1/engine/llm_engine.py +++ b/vllm/v1/engine/llm_engine.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Dict, List, Mapping, Optional, Type, Union from typing_extensions import TypeVar diff --git a/vllm/v1/engine/mm_input_mapper.py b/vllm/v1/engine/mm_input_mapper.py index d83460a40..83a0d9db1 100644 --- a/vllm/v1/engine/mm_input_mapper.py +++ b/vllm/v1/engine/mm_input_mapper.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Any, Dict, List, Optional from vllm.config import ModelConfig diff --git a/vllm/v1/engine/output_processor.py b/vllm/v1/engine/output_processor.py index 234ef8194..aeefd5239 100644 --- a/vllm/v1/engine/output_processor.py +++ b/vllm/v1/engine/output_processor.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import asyncio from dataclasses import dataclass from typing import Dict, List, Optional diff --git a/vllm/v1/engine/processor.py b/vllm/v1/engine/processor.py index 6196c1105..366287951 100644 --- a/vllm/v1/engine/processor.py +++ b/vllm/v1/engine/processor.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import time from typing import Mapping, Optional, Union diff --git a/vllm/v1/executor/abstract.py b/vllm/v1/executor/abstract.py index 131be7598..ac10d43eb 100644 --- a/vllm/v1/executor/abstract.py +++ b/vllm/v1/executor/abstract.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Type from vllm.config import VllmConfig diff --git a/vllm/v1/executor/multiproc_executor.py b/vllm/v1/executor/multiproc_executor.py index f6cf35da0..e3f07172d 100644 --- a/vllm/v1/executor/multiproc_executor.py +++ b/vllm/v1/executor/multiproc_executor.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import os import pickle import signal diff --git a/vllm/v1/kv_cache_interface.py b/vllm/v1/kv_cache_interface.py index 6d5cc32ff..eddfb5949 100644 --- a/vllm/v1/kv_cache_interface.py +++ b/vllm/v1/kv_cache_interface.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from dataclasses import dataclass from typing import Dict, List diff --git a/vllm/v1/metrics/loggers.py b/vllm/v1/metrics/loggers.py index f901822c7..f736e38f1 100644 --- a/vllm/v1/metrics/loggers.py +++ b/vllm/v1/metrics/loggers.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import time from abc import ABC, abstractmethod from typing import List diff --git a/vllm/v1/metrics/stats.py b/vllm/v1/metrics/stats.py index 527750512..88f2c0835 100644 --- a/vllm/v1/metrics/stats.py +++ b/vllm/v1/metrics/stats.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import time from dataclasses import dataclass from typing import TYPE_CHECKING, List diff --git a/vllm/v1/outputs.py b/vllm/v1/outputs.py index 32aee44e3..6e82bffd7 100644 --- a/vllm/v1/outputs.py +++ b/vllm/v1/outputs.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from dataclasses import dataclass from typing import Dict, List, Optional diff --git a/vllm/v1/request.py b/vllm/v1/request.py index 80160c673..0519d9e78 100644 --- a/vllm/v1/request.py +++ b/vllm/v1/request.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import enum from typing import TYPE_CHECKING, List, Optional, Union diff --git a/vllm/v1/sample/metadata.py b/vllm/v1/sample/metadata.py index d60f7eb5d..8e54de345 100644 --- a/vllm/v1/sample/metadata.py +++ b/vllm/v1/sample/metadata.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from dataclasses import dataclass from typing import Dict, List, Optional, Set diff --git a/vllm/v1/sample/ops/penalties.py b/vllm/v1/sample/ops/penalties.py index 2796d0494..ba368b44a 100644 --- a/vllm/v1/sample/ops/penalties.py +++ b/vllm/v1/sample/ops/penalties.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List, Set, Tuple import torch diff --git a/vllm/v1/sample/ops/topk_topp_sampler.py b/vllm/v1/sample/ops/topk_topp_sampler.py index f2007d85c..27431001e 100644 --- a/vllm/v1/sample/ops/topk_topp_sampler.py +++ b/vllm/v1/sample/ops/topk_topp_sampler.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import Dict import torch diff --git a/vllm/v1/sample/sampler.py b/vllm/v1/sample/sampler.py index 9ad665a64..3da7498e0 100644 --- a/vllm/v1/sample/sampler.py +++ b/vllm/v1/sample/sampler.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """A layer that samples the next tokens from the model's outputs.""" from typing import Tuple diff --git a/vllm/v1/serial_utils.py b/vllm/v1/serial_utils.py index b1cd5c118..1791dfa2b 100644 --- a/vllm/v1/serial_utils.py +++ b/vllm/v1/serial_utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import pickle diff --git a/vllm/v1/stats/common.py b/vllm/v1/stats/common.py index 902800e05..09d382638 100644 --- a/vllm/v1/stats/common.py +++ b/vllm/v1/stats/common.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import time from dataclasses import dataclass from dataclasses import field as dataclass_field diff --git a/vllm/v1/utils.py b/vllm/v1/utils.py index 8dfcf2dd7..5494542c1 100644 --- a/vllm/v1/utils.py +++ b/vllm/v1/utils.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import multiprocessing import os import weakref diff --git a/vllm/v1/worker/block_table.py b/vllm/v1/worker/block_table.py index 26a2084b1..8d0785243 100644 --- a/vllm/v1/worker/block_table.py +++ b/vllm/v1/worker/block_table.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from typing import List import numpy as np diff --git a/vllm/v1/worker/gpu_input_batch.py b/vllm/v1/worker/gpu_input_batch.py index 28d8e3905..39708f833 100644 --- a/vllm/v1/worker/gpu_input_batch.py +++ b/vllm/v1/worker/gpu_input_batch.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + # Datastructures defining an input batch from dataclasses import dataclass diff --git a/vllm/v1/worker/gpu_model_runner.py b/vllm/v1/worker/gpu_model_runner.py index a00c00c30..0b5644525 100644 --- a/vllm/v1/worker/gpu_model_runner.py +++ b/vllm/v1/worker/gpu_model_runner.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import gc import time from typing import TYPE_CHECKING, Dict, List, Optional, Tuple, cast diff --git a/vllm/v1/worker/gpu_worker.py b/vllm/v1/worker/gpu_worker.py index a8cf0aec3..0adb69073 100644 --- a/vllm/v1/worker/gpu_worker.py +++ b/vllm/v1/worker/gpu_worker.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """A GPU worker class.""" import gc import os diff --git a/vllm/version.py b/vllm/version.py index 66e189dce..70cd0289b 100644 --- a/vllm/version.py +++ b/vllm/version.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + try: from ._version import __version__, __version_tuple__ except Exception as e: diff --git a/vllm/worker/cache_engine.py b/vllm/worker/cache_engine.py index c427b759b..252fe0660 100644 --- a/vllm/worker/cache_engine.py +++ b/vllm/worker/cache_engine.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """CacheEngine class for managing the KV cache.""" from typing import List diff --git a/vllm/worker/cpu_enc_dec_model_runner.py b/vllm/worker/cpu_enc_dec_model_runner.py index fa6775cbd..71e32c5f7 100644 --- a/vllm/worker/cpu_enc_dec_model_runner.py +++ b/vllm/worker/cpu_enc_dec_model_runner.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import dataclasses from typing import TYPE_CHECKING, Any, Dict, List, Optional, Tuple, Type, cast diff --git a/vllm/worker/cpu_model_runner.py b/vllm/worker/cpu_model_runner.py index 4b429b67b..1c3feece9 100644 --- a/vllm/worker/cpu_model_runner.py +++ b/vllm/worker/cpu_model_runner.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import dataclasses import weakref from collections import defaultdict diff --git a/vllm/worker/cpu_pooling_model_runner.py b/vllm/worker/cpu_pooling_model_runner.py index d31ba89e1..c0744d63b 100644 --- a/vllm/worker/cpu_pooling_model_runner.py +++ b/vllm/worker/cpu_pooling_model_runner.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import dataclasses from typing import Any, Dict, List, Optional, Tuple, Type, Union diff --git a/vllm/worker/cpu_worker.py b/vllm/worker/cpu_worker.py index 3e5fcf11b..27b1a2dd1 100644 --- a/vllm/worker/cpu_worker.py +++ b/vllm/worker/cpu_worker.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """A CPU worker class.""" from typing import Dict, List, Optional, Set, Tuple, Type diff --git a/vllm/worker/enc_dec_model_runner.py b/vllm/worker/enc_dec_model_runner.py index 8a161b740..e2d338f75 100644 --- a/vllm/worker/enc_dec_model_runner.py +++ b/vllm/worker/enc_dec_model_runner.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import dataclasses import itertools from typing import Any, Dict, List, Optional, Tuple, Type, cast diff --git a/vllm/worker/hpu_model_runner.py b/vllm/worker/hpu_model_runner.py index a339c97a8..b846d4387 100644 --- a/vllm/worker/hpu_model_runner.py +++ b/vllm/worker/hpu_model_runner.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + ############################################################################### # Copyright (C) 2024 Habana Labs, Ltd. an Intel Company ############################################################################### diff --git a/vllm/worker/hpu_worker.py b/vllm/worker/hpu_worker.py index aaf9cb40b..a1f31bead 100644 --- a/vllm/worker/hpu_worker.py +++ b/vllm/worker/hpu_worker.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + ############################################################################### # Copyright (C) 2024 Habana Labs, Ltd. an Intel Company ############################################################################### diff --git a/vllm/worker/model_runner.py b/vllm/worker/model_runner.py index 322d91d62..90f08b1df 100644 --- a/vllm/worker/model_runner.py +++ b/vllm/worker/model_runner.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import dataclasses import gc import inspect diff --git a/vllm/worker/model_runner_base.py b/vllm/worker/model_runner_base.py index aef4bdcdd..9e33ef9f1 100644 --- a/vllm/worker/model_runner_base.py +++ b/vllm/worker/model_runner_base.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import dataclasses import pickle from abc import ABC, abstractmethod diff --git a/vllm/worker/multi_step_model_runner.py b/vllm/worker/multi_step_model_runner.py index 4aab09c80..90771e8ac 100644 --- a/vllm/worker/multi_step_model_runner.py +++ b/vllm/worker/multi_step_model_runner.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import dataclasses import functools from dataclasses import dataclass, field diff --git a/vllm/worker/multi_step_tpu_worker.py b/vllm/worker/multi_step_tpu_worker.py index e654f7172..387119998 100644 --- a/vllm/worker/multi_step_tpu_worker.py +++ b/vllm/worker/multi_step_tpu_worker.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import dataclasses from typing import Dict, Optional, Tuple diff --git a/vllm/worker/multi_step_worker.py b/vllm/worker/multi_step_worker.py index 1f982fe10..3518ab2f6 100644 --- a/vllm/worker/multi_step_worker.py +++ b/vllm/worker/multi_step_worker.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import dataclasses from dataclasses import dataclass from typing import Dict, List, Optional, Tuple diff --git a/vllm/worker/neuron_model_runner.py b/vllm/worker/neuron_model_runner.py index 596c26eac..f2093fc42 100644 --- a/vllm/worker/neuron_model_runner.py +++ b/vllm/worker/neuron_model_runner.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import os from dataclasses import dataclass from importlib.util import find_spec diff --git a/vllm/worker/neuron_worker.py b/vllm/worker/neuron_worker.py index e02c72faa..5f0eb0019 100644 --- a/vllm/worker/neuron_worker.py +++ b/vllm/worker/neuron_worker.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """A Neuron worker class.""" from typing import List, Optional, Tuple diff --git a/vllm/worker/openvino_model_runner.py b/vllm/worker/openvino_model_runner.py index 42fe2cf66..44442cddb 100644 --- a/vllm/worker/openvino_model_runner.py +++ b/vllm/worker/openvino_model_runner.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + from collections import defaultdict from typing import Dict, List, NamedTuple, Optional, Tuple diff --git a/vllm/worker/openvino_worker.py b/vllm/worker/openvino_worker.py index f5b46cde3..0690222d9 100644 --- a/vllm/worker/openvino_worker.py +++ b/vllm/worker/openvino_worker.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """An OpenVINO worker class.""" from typing import Any, Dict, List, Optional, Tuple diff --git a/vllm/worker/pooling_model_runner.py b/vllm/worker/pooling_model_runner.py index 6de227f3c..f43085b0e 100644 --- a/vllm/worker/pooling_model_runner.py +++ b/vllm/worker/pooling_model_runner.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import dataclasses from typing import Any, Dict, List, Optional, Tuple, Type, Union diff --git a/vllm/worker/tpu_model_runner.py b/vllm/worker/tpu_model_runner.py index 874951828..ecdf7aa88 100644 --- a/vllm/worker/tpu_model_runner.py +++ b/vllm/worker/tpu_model_runner.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import enum import time from dataclasses import dataclass diff --git a/vllm/worker/tpu_worker.py b/vllm/worker/tpu_worker.py index ea0e70054..12f10169f 100644 --- a/vllm/worker/tpu_worker.py +++ b/vllm/worker/tpu_worker.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import os from typing import List, Optional, Tuple, Union diff --git a/vllm/worker/utils.py b/vllm/worker/utils.py index ffa8c4cb0..d925f0883 100644 --- a/vllm/worker/utils.py +++ b/vllm/worker/utils.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 ''' Worker-related helper functions. ''' diff --git a/vllm/worker/worker.py b/vllm/worker/worker.py index 1d2884d3d..582aa460e 100644 --- a/vllm/worker/worker.py +++ b/vllm/worker/worker.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """A GPU worker class.""" import gc import os diff --git a/vllm/worker/worker_base.py b/vllm/worker/worker_base.py index 6eeb4aa17..819b81fbf 100644 --- a/vllm/worker/worker_base.py +++ b/vllm/worker/worker_base.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import dataclasses import os import time diff --git a/vllm/worker/xpu_model_runner.py b/vllm/worker/xpu_model_runner.py index b7b7b7227..9c726e1a1 100644 --- a/vllm/worker/xpu_model_runner.py +++ b/vllm/worker/xpu_model_runner.py @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: Apache-2.0 + import dataclasses import time import weakref diff --git a/vllm/worker/xpu_worker.py b/vllm/worker/xpu_worker.py index e9cb623c8..047c0bbbc 100644 --- a/vllm/worker/xpu_worker.py +++ b/vllm/worker/xpu_worker.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: Apache-2.0 """A XPU worker class.""" import gc import os -- GitLab