Skip to content

GitLab

Unverified Commit d4a09ec9 authored by Liangsheng Yin's avatar Liangsheng Yin Committed by GitHub
Browse files

[CI] fix tests' time estimation (#12401)

parent 662725b9
Hide whitespace changes
Inline Side-by-side
Showing with 54 additions and 55 deletions
test/srt/run_suite.py
View file @ d4a09ec9
...@@ -21,43 +21,42 @@ suites = { ...@@ -21,43 +21,42 @@ suites = {
TestFile("hicache/test_hicache_storage.py", 127), TestFile("hicache/test_hicache_storage.py", 127),
TestFile("layers/attention/mamba/test_causal_conv1d.py", 25), TestFile("layers/attention/mamba/test_causal_conv1d.py", 25),
TestFile("layers/attention/mamba/test_mamba_ssm.py", 50), TestFile("layers/attention/mamba/test_mamba_ssm.py", 50),
TestFile("layers/attention/mamba/test_mamba_ssm_ssd.py", 70), TestFile("layers/attention/mamba/test_mamba_ssm_ssd.py", 20),
TestFile("lora/test_lora.py", 200), TestFile("lora/test_lora.py", 150),
TestFile("lora/test_lora_eviction.py", 200), TestFile("lora/test_lora_eviction.py", 240),
TestFile("lora/test_lora_eviction_policy.py", 200), TestFile("lora/test_lora_eviction_policy.py", 200),
TestFile("lora/test_lora_backend.py", 99), TestFile("lora/test_lora_backend.py", 99),
TestFile("lora/test_lora_eviction.py", 200),
TestFile("lora/test_lora_qwen3.py", 97), TestFile("lora/test_lora_qwen3.py", 97),
TestFile("lora/test_lora_radix_cache.py", 100), TestFile("lora/test_lora_radix_cache.py", 200),
TestFile("lora/test_lora_openai_api.py", 30), TestFile("lora/test_lora_openai_api.py", 30),
TestFile("lora/test_lora_update.py", 400), TestFile("lora/test_lora_update.py", 600),
TestFile("lora/test_multi_lora_backend.py", 60), TestFile("lora/test_multi_lora_backend.py", 60),
TestFile("models/test_compressed_tensors_models.py", 42), TestFile("models/test_compressed_tensors_models.py", 42),
TestFile("models/test_cross_encoder_models.py", 100), TestFile("models/test_cross_encoder_models.py", 100),
TestFile("models/test_embedding_models.py", 73), TestFile("models/test_embedding_models.py", 73),
TestFile("models/test_encoder_embedding_models.py", 460), TestFile("models/test_encoder_embedding_models.py", 460),
TestFile("models/test_generation_models.py", 103), TestFile("models/test_generation_models.py", 103),
TestFile("models/test_nvidia_nemotron_nano_v2.py", 300), TestFile("models/test_nvidia_nemotron_nano_v2.py", 160),
TestFile("models/test_qwen_models.py", 82), TestFile("models/test_qwen_models.py", 82),
TestFile("batch_invariant/test_batch_invariant_ops.py", 10), TestFile("batch_invariant/test_batch_invariant_ops.py", 10),
TestFile("models/test_reward_models.py", 132), TestFile("models/test_reward_models.py", 132),
TestFile("models/test_transformers_models.py", 320), TestFile("models/test_transformers_models.py", 320),
TestFile("models/test_vlm_models.py", 741), TestFile("models/test_vlm_models.py", 741),
TestFile("openai_server/basic/test_openai_embedding.py", 141), TestFile("openai_server/basic/test_openai_embedding.py", 79),
TestFile("openai_server/basic/test_openai_server.py", 149), TestFile("openai_server/basic/test_openai_server.py", 270),
TestFile("openai_server/basic/test_protocol.py", 10), TestFile("openai_server/basic/test_protocol.py", 10),
TestFile("openai_server/basic/test_serving_chat.py", 10), TestFile("openai_server/basic/test_serving_chat.py", 10),
TestFile("openai_server/basic/test_serving_completions.py", 10), TestFile("openai_server/basic/test_serving_completions.py", 10),
TestFile("openai_server/basic/test_serving_embedding.py", 10), TestFile("openai_server/basic/test_serving_embedding.py", 10),
TestFile("openai_server/features/test_enable_thinking.py", 70), TestFile("openai_server/features/test_enable_thinking.py", 70),
TestFile("openai_server/features/test_json_constrained.py", 98), TestFile("openai_server/features/test_json_constrained.py", 120),
TestFile("openai_server/features/test_json_mode.py", 90), TestFile("openai_server/features/test_json_mode.py", 120),
TestFile("openai_server/features/test_openai_server_ebnf.py", 95), TestFile("openai_server/features/test_openai_server_ebnf.py", 20),
TestFile("openai_server/features/test_openai_server_hidden_states.py", 240), TestFile("openai_server/features/test_openai_server_hidden_states.py", 240),
TestFile("openai_server/features/test_reasoning_content.py", 89), TestFile("openai_server/features/test_reasoning_content.py", 89),
TestFile("openai_server/features/test_lora_openai_compatible.py", 120), TestFile("openai_server/features/test_lora_openai_compatible.py", 150),
TestFile("openai_server/function_call/test_openai_function_calling.py", 60), TestFile("openai_server/function_call/test_openai_function_calling.py", 60),
TestFile("openai_server/function_call/test_tool_choice.py", 226), TestFile("openai_server/function_call/test_tool_choice.py", 120),
TestFile("openai_server/validation/test_large_max_new_tokens.py", 41), TestFile("openai_server/validation/test_large_max_new_tokens.py", 41),
TestFile("openai_server/validation/test_matched_stop.py", 60), TestFile("openai_server/validation/test_matched_stop.py", 60),
TestFile("openai_server/validation/test_openai_server_ignore_eos.py", 85), TestFile("openai_server/validation/test_openai_server_ignore_eos.py", 85),
...@@ -66,27 +65,27 @@ suites = { ...@@ -66,27 +65,27 @@ suites = {
TestFile("quant/test_fp8_kernel.py", 8), TestFile("quant/test_fp8_kernel.py", 8),
TestFile("quant/test_int8_kernel.py", 8), TestFile("quant/test_int8_kernel.py", 8),
TestFile("quant/test_triton_scaled_mm.py", 8), TestFile("quant/test_triton_scaled_mm.py", 8),
TestFile("quant/test_w8a8_quantization.py", 46), TestFile("quant/test_w8a8_quantization.py", 160),
TestFile("quant/test_autoround.py", 60), TestFile("quant/test_autoround.py", 60),
TestFile("rl/test_fp32_lm_head.py", 30), TestFile("rl/test_fp32_lm_head.py", 30),
TestFile("rl/test_update_weights_from_disk.py", 114), TestFile("rl/test_update_weights_from_disk.py", 210),
TestFile("rl/test_update_weights_from_tensor.py", 48), TestFile("rl/test_update_weights_from_tensor.py", 80),
TestFile("test_abort.py", 121), TestFile("test_abort.py", 190),
TestFile("test_build_eagle_tree.py", 8), TestFile("test_build_eagle_tree.py", 8),
TestFile("test_chunked_prefill.py", 313), TestFile("test_chunked_prefill.py", 410),
TestFile("test_create_kvindices.py", 2), TestFile("test_create_kvindices.py", 2),
TestFile("test_deterministic.py", 320), TestFile("test_deterministic.py", 320),
TestFile("test_eagle_infer_a.py", 370), TestFile("test_eagle_infer_a.py", 370),
TestFile("test_eagle_infer_b.py", 700), TestFile("test_eagle_infer_b.py", 500),
TestFile("test_eagle_infer_beta.py", 90), TestFile("test_eagle_infer_beta.py", 90),
TestFile("test_ebnf_constrained.py", 108), TestFile("test_ebnf_constrained.py", 80),
TestFile("test_eval_fp8_accuracy.py", 303), TestFile("test_eval_fp8_accuracy.py", 303),
TestFile("test_fa3.py", 376), TestFile("test_fa3.py", 420),
TestFile("test_flashmla.py", 352), TestFile("test_flashmla.py", 230),
TestFile("rotary_embedding/test_mrope.py", 300), TestFile("rotary_embedding/test_mrope.py", 10),
TestFile("test_function_call_parser.py", 10), TestFile("test_function_call_parser.py", 10),
TestFile("test_fused_moe.py", 30), TestFile("test_fused_moe.py", 80),
TestFile("test_gpt_oss_1gpu.py", 600), TestFile("test_gpt_oss_1gpu.py", 750),
TestFile("test_harmony_parser.py", 20), TestFile("test_harmony_parser.py", 20),
TestFile("test_hidden_states.py", 55), TestFile("test_hidden_states.py", 55),
TestFile("test_hybrid_attn_backend.py", 379), TestFile("test_hybrid_attn_backend.py", 379),
...@@ -96,49 +95,49 @@ suites = { ...@@ -96,49 +95,49 @@ suites = {
TestFile("test_mamba_unittest.py", 4), TestFile("test_mamba_unittest.py", 4),
TestFile("test_metrics.py", 32), TestFile("test_metrics.py", 32),
TestFile("test_metrics_utils.py", 1), TestFile("test_metrics_utils.py", 1),
TestFile("test_mla.py", 167), TestFile("test_mla.py", 180),
TestFile("test_mla_deepseek_v3.py", 500), TestFile("test_mla_deepseek_v3.py", 500),
TestFile("test_mla_flashinfer.py", 302), TestFile("test_mla_flashinfer.py", 302),
TestFile("test_mla_fp8.py", 93), TestFile("test_mla_fp8.py", 93),
TestFile("test_mla_int8_deepseek_v3.py", 429), TestFile("test_mla_int8_deepseek_v3.py", 300),
TestFile("test_modelopt_loader.py", 30), TestFile("test_modelopt_loader.py", 30),
TestFile("test_multi_tokenizer.py", 230), TestFile("test_multi_tokenizer.py", 230),
TestFile("test_ngram_speculative_decoding.py", 250), TestFile("test_ngram_speculative_decoding.py", 290),
TestFile("test_no_chunked_prefill.py", 108), TestFile("test_no_chunked_prefill.py", 108),
TestFile("test_no_overlap_scheduler.py", 234), TestFile("test_no_overlap_scheduler.py", 234),
TestFile("test_original_logprobs.py", 41), TestFile("test_original_logprobs.py", 41),
TestFile("test_page_size.py", 60), TestFile("test_page_size.py", 60),
TestFile("test_penalty.py", 41), TestFile("test_penalty.py", 41),
TestFile("test_priority_scheduling.py", 100), TestFile("test_priority_scheduling.py", 130),
TestFile("test_pytorch_sampling_backend.py", 66), TestFile("test_pytorch_sampling_backend.py", 66),
TestFile("test_radix_attention.py", 105), TestFile("test_radix_attention.py", 105),
TestFile("test_radix_cache_unit.py", 5), TestFile("test_radix_cache_unit.py", 5),
TestFile("test_reasoning_parser.py", 5), TestFile("test_reasoning_parser.py", 5),
TestFile("test_regex_constrained.py", 64), TestFile("test_regex_constrained.py", 64),
TestFile("test_request_queue_validation.py", 30), TestFile("test_request_queue_validation.py", 30),
TestFile("test_retract_decode.py", 90), TestFile("test_retract_decode.py", 450),
TestFile("test_score_api.py", 310), TestFile("test_score_api.py", 310),
TestFile("test_server_args.py", 1), TestFile("test_server_args.py", 1),
TestFile("test_speculative_registry.py", 1), TestFile("test_speculative_registry.py", 1),
TestFile("test_skip_tokenizer_init.py", 117), TestFile("test_skip_tokenizer_init.py", 117),
TestFile("test_srt_endpoint.py", 130), TestFile("test_srt_endpoint.py", 130),
TestFile("test_srt_engine.py", 261), TestFile("test_srt_engine.py", 261),
TestFile("test_standalone_speculative_decoding.py", 250), TestFile("test_standalone_speculative_decoding.py", 150),
TestFile("test_start_profile.py", 60), TestFile("test_start_profile.py", 60),
TestFile("test_profile_merger.py", 60), TestFile("test_profile_merger.py", 60),
TestFile("test_profile_merger_http_api.py", 15), TestFile("test_profile_merger_http_api.py", 15),
TestFile("test_swa_unittest.py", 1), TestFile("test_swa_unittest.py", 1),
TestFile("test_torch_compile.py", 76), TestFile("test_torch_compile.py", 76),
TestFile("test_torch_compile_moe.py", 172), TestFile("test_torch_compile_moe.py", 210),
TestFile("test_torch_native_attention_backend.py", 123), TestFile("test_torch_native_attention_backend.py", 123),
TestFile("test_torchao.py", 70), TestFile("test_torchao.py", 70),
TestFile("test_triton_attention_backend.py", 150), TestFile("test_triton_attention_backend.py", 150),
TestFile("test_triton_attention_kernels.py", 4), TestFile("test_triton_attention_kernels.py", 4),
TestFile("test_triton_moe_channel_fp8_kernel.py", 25), TestFile("test_triton_moe_channel_fp8_kernel.py", 25),
TestFile("test_triton_sliding_window.py", 250), TestFile("test_triton_sliding_window.py", 100),
TestFile("test_utils_update_weights.py", 48), TestFile("test_utils_update_weights.py", 48),
TestFile("test_vision_chunked_prefill.py", 175), TestFile("test_vision_chunked_prefill.py", 170),
TestFile("test_vision_openai_server_a.py", 918), TestFile("test_vision_openai_server_a.py", 900),
TestFile("test_vlm_input_format.py", 300), TestFile("test_vlm_input_format.py", 300),
TestFile("test_modelopt_loader.py", 30), TestFile("test_modelopt_loader.py", 30),
TestFile("test_modelopt_export.py", 30), TestFile("test_modelopt_export.py", 30),
...@@ -147,17 +146,17 @@ suites = { ...@@ -147,17 +146,17 @@ suites = {
TestFile("ep/test_moe_ep.py", 140), TestFile("ep/test_moe_ep.py", 140),
TestFile("hicache/test_hicache_storage_3fs_backend.py", 200), TestFile("hicache/test_hicache_storage_3fs_backend.py", 200),
TestFile("hicache/test_hicache_storage_file_backend.py", 200), TestFile("hicache/test_hicache_storage_file_backend.py", 200),
TestFile("hicache/test_hicache_storage_mooncake_backend.py", 400), TestFile("hicache/test_hicache_storage_mooncake_backend.py", 300),
TestFile("layers/attention/mamba/test_mamba2_mixer.py", 50), TestFile("layers/attention/mamba/test_mamba2_mixer.py", 50),
TestFile("lora/test_lora_tp.py", 116), TestFile("lora/test_lora_tp.py", 116),
TestFile("models/test_glm4_moe_models.py", 100), TestFile("models/test_glm4_moe_models.py", 100),
TestFile("rl/test_update_weights_from_distributed.py", 103), TestFile("rl/test_update_weights_from_distributed.py", 103),
TestFile("test_data_parallelism.py", 73), TestFile("test_data_parallelism.py", 73),
TestFile("test_disaggregation_basic.py", 400), TestFile("test_disaggregation_basic.py", 400),
TestFile("test_dp_attention.py", 594), TestFile("test_dp_attention.py", 350),
TestFile("test_load_weights_from_remote_instance.py", 72), TestFile("test_load_weights_from_remote_instance.py", 72),
TestFile("test_patch_torch.py", 19), TestFile("test_patch_torch.py", 19),
TestFile("test_release_memory_occupation.py", 257), TestFile("test_release_memory_occupation.py", 200),
TestFile("test_eagle_dp_attention.py", 200), TestFile("test_eagle_dp_attention.py", 200),
], ],
"per-commit-4-gpu": [ "per-commit-4-gpu": [
...@@ -220,43 +219,43 @@ suite_amd = { ...@@ -220,43 +219,43 @@ suite_amd = {
TestFile("hicache/test_hicache.py", 116), TestFile("hicache/test_hicache.py", 116),
TestFile("hicache/test_hicache_mla.py", 127), TestFile("hicache/test_hicache_mla.py", 127),
TestFile("hicache/test_hicache_storage.py", 127), TestFile("hicache/test_hicache_storage.py", 127),
TestFile("lora/test_lora.py", 200), TestFile("lora/test_lora.py", 150),
TestFile("lora/test_lora_backend.py", 99), TestFile("lora/test_lora_backend.py", 99),
TestFile("lora/test_lora_cuda_graph.py", 250), TestFile("lora/test_lora_cuda_graph.py", 250),
TestFile("lora/test_lora_eviction.py", 200), TestFile("lora/test_lora_eviction.py", 240),
TestFile("lora/test_lora_qwen3.py", 97), TestFile("lora/test_lora_qwen3.py", 97),
TestFile("lora/test_multi_lora_backend.py", 60), TestFile("lora/test_multi_lora_backend.py", 60),
TestFile("models/test_compressed_tensors_models.py", 42), TestFile("models/test_compressed_tensors_models.py", 42),
TestFile("models/test_qwen_models.py", 82), TestFile("models/test_qwen_models.py", 82),
TestFile("models/test_reward_models.py", 132), TestFile("models/test_reward_models.py", 132),
TestFile("models/test_transformers_models.py", 320), TestFile("models/test_transformers_models.py", 320),
TestFile("openai_server/basic/test_openai_embedding.py", 141), TestFile("openai_server/basic/test_openai_embedding.py", 79),
TestFile("openai_server/basic/test_openai_server.py", 149), TestFile("openai_server/basic/test_openai_server.py", 270),
TestFile("openai_server/basic/test_protocol.py", 10), TestFile("openai_server/basic/test_protocol.py", 10),
TestFile("openai_server/basic/test_serving_chat.py", 10), TestFile("openai_server/basic/test_serving_chat.py", 10),
TestFile("openai_server/basic/test_serving_completions.py", 10), TestFile("openai_server/basic/test_serving_completions.py", 10),
TestFile("openai_server/basic/test_serving_embedding.py", 10), TestFile("openai_server/basic/test_serving_embedding.py", 10),
TestFile("openai_server/features/test_enable_thinking.py", 70), TestFile("openai_server/features/test_enable_thinking.py", 70),
TestFile("openai_server/features/test_json_constrained.py", 98), TestFile("openai_server/features/test_json_constrained.py", 120),
TestFile("openai_server/features/test_json_mode.py", 90), TestFile("openai_server/features/test_json_mode.py", 120),
TestFile("openai_server/features/test_openai_server_ebnf.py", 95), TestFile("openai_server/features/test_openai_server_ebnf.py", 20),
TestFile("openai_server/features/test_reasoning_content.py", 89), TestFile("openai_server/features/test_reasoning_content.py", 89),
TestFile("openai_server/function_call/test_openai_function_calling.py", 60), TestFile("openai_server/function_call/test_openai_function_calling.py", 60),
TestFile("openai_server/function_call/test_tool_choice.py", 226), TestFile("openai_server/function_call/test_tool_choice.py", 120),
TestFile("openai_server/validation/test_large_max_new_tokens.py", 41), TestFile("openai_server/validation/test_large_max_new_tokens.py", 41),
TestFile("openai_server/validation/test_matched_stop.py", 60), TestFile("openai_server/validation/test_matched_stop.py", 60),
TestFile("openai_server/validation/test_openai_server_ignore_eos.py", 85), TestFile("openai_server/validation/test_openai_server_ignore_eos.py", 85),
TestFile("openai_server/validation/test_request_length_validation.py", 31), TestFile("openai_server/validation/test_request_length_validation.py", 31),
TestFile("quant/test_awq_dequant.py", 2), TestFile("quant/test_awq_dequant.py", 2),
TestFile("quant/test_block_int8.py", 22), TestFile("quant/test_block_int8.py", 22),
TestFile("rl/test_update_weights_from_disk.py", 114), TestFile("rl/test_update_weights_from_disk.py", 210),
TestFile("test_abort.py", 51), TestFile("test_abort.py", 51),
TestFile("test_chunked_prefill.py", 313), TestFile("test_chunked_prefill.py", 410),
TestFile("test_create_kvindices.py", 2), TestFile("test_create_kvindices.py", 2),
TestFile("test_ebnf_constrained.py", 108), TestFile("test_ebnf_constrained.py", 80),
TestFile("test_eval_fp8_accuracy.py", 303), TestFile("test_eval_fp8_accuracy.py", 303),
TestFile("test_function_call_parser.py", 10), TestFile("test_function_call_parser.py", 10),
TestFile("test_fused_moe.py", 30), TestFile("test_fused_moe.py", 80),
TestFile("test_input_embeddings.py", 38), TestFile("test_input_embeddings.py", 38),
TestFile("test_io_struct.py", 8), TestFile("test_io_struct.py", 8),
TestFile("test_jinja_template_utils.py", 1), TestFile("test_jinja_template_utils.py", 1),
...@@ -271,16 +270,16 @@ suite_amd = { ...@@ -271,16 +270,16 @@ suite_amd = {
TestFile("test_radix_attention.py", 105), TestFile("test_radix_attention.py", 105),
TestFile("test_reasoning_parser.py", 5), TestFile("test_reasoning_parser.py", 5),
TestFile("test_regex_constrained.py", 64), TestFile("test_regex_constrained.py", 64),
TestFile("test_retract_decode.py", 54), TestFile("test_retract_decode.py", 450),
TestFile("test_rope_rocm.py", 3), TestFile("test_rope_rocm.py", 3),
TestFile("test_server_args.py", 1), TestFile("test_server_args.py", 1),
TestFile("test_skip_tokenizer_init.py", 117), TestFile("test_skip_tokenizer_init.py", 117),
TestFile("test_srt_endpoint.py", 130), TestFile("test_srt_endpoint.py", 130),
TestFile("test_srt_engine.py", 261), TestFile("test_srt_engine.py", 261),
TestFile("test_torch_compile.py", 169), TestFile("test_torch_compile.py", 169),
TestFile("test_torch_compile_moe.py", 172), TestFile("test_torch_compile_moe.py", 210),
TestFile("test_torch_native_attention_backend.py", 123), TestFile("test_torch_native_attention_backend.py", 123),
TestFile("test_triton_attention_backend.py", 150), TestFile("test_triton_attention_backend.py", 250),
TestFile("test_wave_attention_kernels.py", 2), TestFile("test_wave_attention_kernels.py", 2),
# Disabled temporarily # Disabled temporarily
# TestFile("models/test_embedding_models.py", 73), # Disabled temporarily, see https://github.com/sgl-project/sglang/issues/11127 # TestFile("models/test_embedding_models.py", 73), # Disabled temporarily, see https://github.com/sgl-project/sglang/issues/11127
...@@ -291,7 +290,7 @@ suite_amd = { ...@@ -291,7 +290,7 @@ suite_amd = {
# TestFile("test_wave_attention_backend.py", 150), # Disabled temporarily, see https://github.com/sgl-project/sglang/issues/11127 # TestFile("test_wave_attention_backend.py", 150), # Disabled temporarily, see https://github.com/sgl-project/sglang/issues/11127
], ],
"per-commit-amd-mi35x": [ "per-commit-amd-mi35x": [
TestFile("test_gpt_oss_1gpu.py", 600), TestFile("test_gpt_oss_1gpu.py", 750),
TestFile("test_mla.py", 242), TestFile("test_mla.py", 242),
], ],
"per-commit-2-gpu-amd": [ "per-commit-2-gpu-amd": [
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment