Skip to content

GitLab

Commit 3fb4b5fa authored by zhuwenwen's avatar zhuwenwen
Browse files

Merge tag 'v0.18.0' into v0.18.0-ori

parents bcf25339 89138b21
Hide whitespace changes
Inline Side-by-side
Showing with 406 additions and 157 deletions
.buildkite/test_areas/expert_parallelism.yaml
View file @ 3fb4b5fa
...@@ -20,4 +20,19 @@ steps: ...@@ -20,4 +20,19 @@ steps:
- tests/distributed/test_eplb_execute.py - tests/distributed/test_eplb_execute.py
commands: commands:
- pytest -v -s distributed/test_eplb_execute.py - pytest -v -s distributed/test_eplb_execute.py
- pytest -v -s distributed/test_eplb_spec_decode.py - pytest -v -s distributed/test_eplb_spec_decode.py
\ No newline at end of file
- label: Elastic EP Scaling Test
timeout_in_minutes: 20
device: b200
optional: true
working_dir: "/vllm-workspace/tests"
num_devices: 4
source_file_dependencies:
- vllm/distributed/
- vllm/engine/
- vllm/executor/
- vllm/compilation/
- tests/distributed/
commands:
- pytest -v -s distributed/test_elastic_ep.py
.buildkite/test_areas/kernels.yaml
View file @ 3fb4b5fa
...@@ -8,8 +8,9 @@ steps: ...@@ -8,8 +8,9 @@ steps:
- csrc/ - csrc/
- tests/kernels/core - tests/kernels/core
- tests/kernels/test_top_k_per_row.py - tests/kernels/test_top_k_per_row.py
- tests/kernels/test_concat_mla_q.py
commands: commands:
- pytest -v -s kernels/core kernels/test_top_k_per_row.py - pytest -v -s kernels/core kernels/test_top_k_per_row.py kernels/test_concat_mla_q.py
- label: Kernels Attention Test %N - label: Kernels Attention Test %N
timeout_in_minutes: 35 timeout_in_minutes: 35
...@@ -44,7 +45,8 @@ steps: ...@@ -44,7 +45,8 @@ steps:
- vllm/envs.py - vllm/envs.py
- vllm/config - vllm/config
commands: commands:
- pytest -v -s kernels/moe --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT - pytest -v -s kernels/moe --ignore=kernels/moe/test_modular_oai_triton_moe.py --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT
- pytest -v -s kernels/moe/test_modular_oai_triton_moe.py --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT
parallelism: 2 parallelism: 2
- label: Kernels Mamba Test - label: Kernels Mamba Test
...@@ -70,7 +72,7 @@ steps: ...@@ -70,7 +72,7 @@ steps:
- tests/kernels/moe/test_batched_deepgemm.py - tests/kernels/moe/test_batched_deepgemm.py
- tests/kernels/attention/test_deepgemm_attention.py - tests/kernels/attention/test_deepgemm_attention.py
commands: commands:
- pytest -v -s kernels/quantization/test_block_fp8.py -k deep_gemm - pytest -v -s kernels/quantization/test_block_fp8.py
- pytest -v -s kernels/moe/test_deepgemm.py - pytest -v -s kernels/moe/test_deepgemm.py
- pytest -v -s kernels/moe/test_batched_deepgemm.py - pytest -v -s kernels/moe/test_batched_deepgemm.py
- pytest -v -s kernels/attention/test_deepgemm_attention.py - pytest -v -s kernels/attention/test_deepgemm_attention.py
...@@ -95,7 +97,7 @@ steps: ...@@ -95,7 +97,7 @@ steps:
- vllm/platforms/cuda.py - vllm/platforms/cuda.py
commands: commands:
- nvidia-smi - nvidia-smi
- python3 examples/offline_inference/basic/chat.py - python3 examples/basic/offline_inference/chat.py
# Attention # Attention
# num_heads2 broken by https://github.com/flashinfer-ai/flashinfer/issues/1353 # num_heads2 broken by https://github.com/flashinfer-ai/flashinfer/issues/1353
- pytest -v -s tests/kernels/attention/test_attention_selector.py - pytest -v -s tests/kernels/attention/test_attention_selector.py
...@@ -115,6 +117,7 @@ steps: ...@@ -115,6 +117,7 @@ steps:
- pytest -v -s tests/kernels/moe/test_nvfp4_moe.py - pytest -v -s tests/kernels/moe/test_nvfp4_moe.py
- pytest -v -s tests/kernels/moe/test_ocp_mx_moe.py - pytest -v -s tests/kernels/moe/test_ocp_mx_moe.py
- pytest -v -s tests/kernels/moe/test_flashinfer.py - pytest -v -s tests/kernels/moe/test_flashinfer.py
- pytest -v -s tests/kernels/moe/test_flashinfer_moe.py
- pytest -v -s tests/kernels/moe/test_cutedsl_moe.py - pytest -v -s tests/kernels/moe/test_cutedsl_moe.py
# e2e # e2e
- pytest -v -s tests/models/quantization/test_nvfp4.py - pytest -v -s tests/models/quantization/test_nvfp4.py
...@@ -154,9 +157,7 @@ steps: ...@@ -154,9 +157,7 @@ steps:
commands: commands:
- pytest -v -s kernels/moe/test_deepep_deepgemm_moe.py - pytest -v -s kernels/moe/test_deepep_deepgemm_moe.py
- pytest -v -s kernels/moe/test_deepep_moe.py - pytest -v -s kernels/moe/test_deepep_moe.py
- pytest -v -s kernels/moe/test_pplx_cutlass_moe.py
# - pytest -v -s kernels/moe/test_pplx_moe.py - failing on main
- label: Kernels Fp4 MoE Test (B200) - label: Kernels Fp4 MoE Test (B200)
timeout_in_minutes: 60 timeout_in_minutes: 60
device: b200 device: b200
......
.buildkite/test_areas/lm_eval.yaml
View file @ 3fb4b5fa
...@@ -11,17 +11,17 @@ steps: ...@@ -11,17 +11,17 @@ steps:
commands: commands:
- pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-small.txt - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-small.txt
- label: LM Eval Large Models (4 GPUs)(A100) # - label: LM Eval Large Models (4 GPUs)(A100)
device: a100 # device: a100
optional: true # optional: true
num_devices: 4 # num_devices: 4
working_dir: "/vllm-workspace/.buildkite/lm-eval-harness" # working_dir: "/vllm-workspace/.buildkite/lm-eval-harness"
source_file_dependencies: # source_file_dependencies:
- csrc/ # - csrc/
- vllm/model_executor/layers/quantization # - vllm/model_executor/layers/quantization
commands: # commands:
- export VLLM_WORKER_MULTIPROC_METHOD=spawn # - export VLLM_WORKER_MULTIPROC_METHOD=spawn
- pytest -s -v test_lm_eval_correctness.py --config-list-file=configs/models-large.txt --tp-size=4 # - pytest -s -v test_lm_eval_correctness.py --config-list-file=configs/models-large.txt --tp-size=4
- label: LM Eval Large Models (4 GPUs)(H100) - label: LM Eval Large Models (4 GPUs)(H100)
device: h100 device: h100
...@@ -73,3 +73,29 @@ steps: ...@@ -73,3 +73,29 @@ steps:
num_devices: 2 num_devices: 2
commands: commands:
- pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=evals/gsm8k/configs/moe-refactor-dp-ep/config-b200.txt - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=evals/gsm8k/configs/moe-refactor-dp-ep/config-b200.txt
- label: GPQA Eval (GPT-OSS) (H100)
timeout_in_minutes: 120
device: h100
optional: true
num_devices: 2
source_file_dependencies:
- csrc/
- vllm/model_executor/layers/quantization
- tests/evals/gpt_oss/
commands:
- uv pip install --system 'gpt-oss[eval]==0.0.5'
- pytest -s -v evals/gpt_oss/test_gpqa_correctness.py --config-list-file=configs/models-h100.txt
- label: GPQA Eval (GPT-OSS) (B200)
timeout_in_minutes: 120
device: b200
optional: true
num_devices: 2
source_file_dependencies:
- csrc/
- vllm/model_executor/layers/quantization
- tests/evals/gpt_oss/
commands:
- uv pip install --system 'gpt-oss[eval]==0.0.5'
- pytest -s -v evals/gpt_oss/test_gpqa_correctness.py --config-list-file=configs/models-b200.txt
.buildkite/test_areas/misc.yaml
View file @ 3fb4b5fa
...@@ -9,6 +9,7 @@ steps: ...@@ -9,6 +9,7 @@ steps:
- tests/v1 - tests/v1
commands: commands:
- uv pip install --system -r /vllm-workspace/requirements/kv_connectors.txt - uv pip install --system -r /vllm-workspace/requirements/kv_connectors.txt
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
# split the test to avoid interference # split the test to avoid interference
- pytest -v -s -m 'not cpu_test' v1/core - pytest -v -s -m 'not cpu_test' v1/core
- pytest -v -s v1/executor - pytest -v -s v1/executor
...@@ -16,6 +17,7 @@ steps: ...@@ -16,6 +17,7 @@ steps:
- pytest -v -s v1/sample - pytest -v -s v1/sample
- pytest -v -s v1/logits_processors - pytest -v -s v1/logits_processors
- pytest -v -s v1/worker - pytest -v -s v1/worker
# TODO: create another `optional` test group for slow tests
- pytest -v -s -m 'not slow_test' v1/spec_decode - pytest -v -s -m 'not slow_test' v1/spec_decode
- pytest -v -s -m 'not cpu_test' v1/kv_connector/unit - pytest -v -s -m 'not cpu_test' v1/kv_connector/unit
- pytest -v -s -m 'not cpu_test' v1/metrics - pytest -v -s -m 'not cpu_test' v1/metrics
...@@ -25,6 +27,11 @@ steps: ...@@ -25,6 +27,11 @@ steps:
# Integration test for streaming correctness (requires special branch). # Integration test for streaming correctness (requires special branch).
- pip install -U git+https://github.com/robertgshaw2-redhat/lm-evaluation-harness.git@streaming-api - pip install -U git+https://github.com/robertgshaw2-redhat/lm-evaluation-harness.git@streaming-api
- pytest -v -s entrypoints/openai/correctness/test_lmeval.py::test_lm_eval_accuracy_v1_engine - pytest -v -s entrypoints/openai/correctness/test_lmeval.py::test_lm_eval_accuracy_v1_engine
mirror:
amd:
device: mi325_1
depends_on:
- image-build-amd
- label: V1 Others (CPU) - label: V1 Others (CPU)
depends_on: depends_on:
...@@ -60,12 +67,13 @@ steps: ...@@ -60,12 +67,13 @@ steps:
- examples/ - examples/
commands: commands:
- pip install tensorizer # for tensorizer test - pip install tensorizer # for tensorizer test
- python3 offline_inference/basic/chat.py # for basic # for basic
- python3 offline_inference/basic/generate.py --model facebook/opt-125m - python3 basic/offline_inference/chat.py
- python3 offline_inference/basic/generate.py --model meta-llama/Llama-2-13b-chat-hf --cpu-offload-gb 10 - python3 basic/offline_inference/generate.py --model facebook/opt-125m
- python3 offline_inference/basic/classify.py - python3 basic/offline_inference/generate.py --model meta-llama/Llama-2-13b-chat-hf --cpu-offload-gb 10
- python3 offline_inference/basic/embed.py - python3 basic/offline_inference/classify.py
- python3 offline_inference/basic/score.py - python3 basic/offline_inference/embed.py
- python3 basic/offline_inference/score.py
# for multi-modal models # for multi-modal models
- python3 offline_inference/audio_language.py --seed 0 - python3 offline_inference/audio_language.py --seed 0
- python3 offline_inference/vision_language.py --seed 0 - python3 offline_inference/vision_language.py --seed 0
...@@ -108,9 +116,11 @@ steps: ...@@ -108,9 +116,11 @@ steps:
timeout_in_minutes: 50 timeout_in_minutes: 50
source_file_dependencies: source_file_dependencies:
- vllm/ - vllm/
- tests/detokenizer
- tests/multimodal - tests/multimodal
- tests/utils_ - tests/utils_
commands: commands:
- pytest -v -s detokenizer
- pytest -v -s -m 'not cpu_test' multimodal - pytest -v -s -m 'not cpu_test' multimodal
- pytest -v -s utils_ - pytest -v -s utils_
...@@ -123,6 +133,7 @@ steps: ...@@ -123,6 +133,7 @@ steps:
- tests/test_inputs.py - tests/test_inputs.py
- tests/test_outputs.py - tests/test_outputs.py
- tests/test_pooling_params.py - tests/test_pooling_params.py
- tests/test_ray_env.py
- tests/multimodal - tests/multimodal
- tests/renderers - tests/renderers
- tests/standalone_tests/lazy_imports.py - tests/standalone_tests/lazy_imports.py
...@@ -136,6 +147,7 @@ steps: ...@@ -136,6 +147,7 @@ steps:
- pytest -v -s test_inputs.py - pytest -v -s test_inputs.py
- pytest -v -s test_outputs.py - pytest -v -s test_outputs.py
- pytest -v -s test_pooling_params.py - pytest -v -s test_pooling_params.py
- pytest -v -s test_ray_env.py
- pytest -v -s -m 'cpu_test' multimodal - pytest -v -s -m 'cpu_test' multimodal
- pytest -v -s renderers - pytest -v -s renderers
- pytest -v -s tokenizers_ - pytest -v -s tokenizers_
...@@ -143,20 +155,6 @@ steps: ...@@ -143,20 +155,6 @@ steps:
- pytest -v -s transformers_utils - pytest -v -s transformers_utils
- pytest -v -s config - pytest -v -s config
- label: GPT-OSS Eval (B200)
timeout_in_minutes: 60
working_dir: "/vllm-workspace/"
device: b200
optional: true
source_file_dependencies:
- tests/evals/gpt_oss
- vllm/model_executor/models/gpt_oss.py
- vllm/model_executor/layers/quantization/mxfp4.py
- vllm/v1/attention/backends/flashinfer.py
commands:
- uv pip install --system 'gpt-oss[eval]==0.0.5'
- pytest -s -v tests/evals/gpt_oss/test_gpqa_correctness.py --model openai/gpt-oss-20b --metric 0.58
- label: Batch Invariance (H100) - label: Batch Invariance (H100)
timeout_in_minutes: 25 timeout_in_minutes: 25
device: h100 device: h100
......
.buildkite/test_areas/model_runner_v2.yaml 0 → 100644
View file @ 3fb4b5fa
group: Model Runner V2
depends_on:
- image-build
steps:
- label: Model Runner V2 Core Tests
timeout_in_minutes: 45
source_file_dependencies:
- vllm/v1/worker/gpu/
- vllm/v1/worker/gpu_worker.py
- vllm/v1/core/sched/
- vllm/v1/attention/
- tests/v1/engine/test_llm_engine.py
- tests/v1/e2e/
- tests/v1/entrypoints/llm/test_struct_output_generate.py
commands:
- set -x
- export VLLM_USE_V2_MODEL_RUNNER=1
- pytest -v -s v1/engine/test_llm_engine.py -k "not test_engine_metrics"
# This requires eager until we sort out CG correctness issues.
# TODO: remove ENFORCE_EAGER here after https://github.com/vllm-project/vllm/pull/32936 is merged.
- ENFORCE_EAGER=1 pytest -v -s v1/e2e/general/test_async_scheduling.py -k "not ngram"
- pytest -v -s v1/e2e/general/test_context_length.py
- pytest -v -s v1/e2e/general/test_min_tokens.py
# Temporary hack filter to exclude ngram spec decoding based tests.
- pytest -v -s v1/entrypoints/llm/test_struct_output_generate.py -k "xgrammar and not speculative_config6 and not speculative_config7 and not speculative_config8 and not speculative_config0"
- label: Model Runner V2 Examples
timeout_in_minutes: 45
working_dir: "/vllm-workspace/examples"
source_file_dependencies:
- vllm/v1/worker/gpu/
- vllm/v1/core/sched/
- vllm/v1/worker/gpu_worker.py
- examples/offline_inference/
- examples/basic/offline_inference/
- examples/pooling/embed/vision_embedding_offline.py
- examples/others/tensorize_vllm_model.py
commands:
- set -x
- export VLLM_USE_V2_MODEL_RUNNER=1
- pip install tensorizer # for tensorizer test
- python3 basic/offline_inference/chat.py # for basic
- python3 basic/offline_inference/generate.py --model facebook/opt-125m
#- python3 basic/offline_inference/generate.py --model meta-llama/Llama-2-13b-chat-hf --cpu-offload-gb 10 # TODO
#- python3 basic/offline_inference/embed.py # TODO
# for multi-modal models
- python3 offline_inference/audio_language.py --seed 0
- python3 offline_inference/vision_language.py --seed 0
- python3 offline_inference/vision_language_multi_image.py --seed 0
- python3 offline_inference/encoder_decoder_multimodal.py --model-type whisper --seed 0
# for pooling models
- python3 pooling/embed/vision_embedding_offline.py --seed 0
# for features demo
- python3 offline_inference/prefix_caching.py
- python3 offline_inference/llm_engine_example.py
- python3 others/tensorize_vllm_model.py --model facebook/opt-125m serialize --serialized-directory /tmp/ --suffix v1 && python3 others/tensorize_vllm_model.py --model facebook/opt-125m deserialize --path-to-tensors /tmp/vllm/facebook/opt-125m/v1/model.tensors
- python3 offline_inference/spec_decode.py --test --method eagle --num_spec_tokens 3 --dataset-name hf --dataset-path philschmid/mt-bench --num-prompts 80 --temp 0 --top-p 1.0 --top-k -1 --tp 1 --enable-chunked-prefill --max-model-len 2048
# https://github.com/vllm-project/vllm/pull/26682 uses slightly more memory in PyTorch 2.9+ causing this test to OOM in 1xL4 GPU
- python3 offline_inference/spec_decode.py --test --method eagle3 --num_spec_tokens 3 --dataset-name hf --dataset-path philschmid/mt-bench --num-prompts 80 --temp 0 --top-p 1.0 --top-k -1 --tp 1 --enable-chunked-prefill --max-model-len 1536
- label: Model Runner V2 Distributed (2 GPUs)
timeout_in_minutes: 45
working_dir: "/vllm-workspace/tests"
num_devices: 2
source_file_dependencies:
- vllm/v1/worker/gpu/
- vllm/v1/worker/gpu_worker.py
- tests/basic_correctness/test_basic_correctness.py
- tests/v1/distributed/test_async_llm_dp.py
- tests/v1/distributed/test_eagle_dp.py
commands:
- set -x
- export VLLM_USE_V2_MODEL_RUNNER=1
# The "and not True" here is a hacky way to exclude the prompt_embeds cases which aren't yet supported.
- TARGET_TEST_SUITE=L4 pytest -v -s basic_correctness/test_basic_correctness.py -m 'distributed(num_gpus=2)' -k "not ray and not True"
# https://github.com/NVIDIA/nccl/issues/1838
- export NCCL_CUMEM_HOST_ENABLE=0
- TP_SIZE=1 DP_SIZE=2 pytest -v -s v1/distributed/test_async_llm_dp.py -k "not ray"
- TP_SIZE=1 DP_SIZE=2 pytest -v -s v1/distributed/test_eagle_dp.py
# These require fix https://github.com/vllm-project/vllm/pull/36280
- label: Model Runner V2 Pipeline Parallelism (4 GPUs)
timeout_in_minutes: 60
working_dir: "/vllm-workspace/tests"
num_devices: 4
source_file_dependencies:
- vllm/v1/worker/gpu/
- vllm/v1/worker/gpu_worker.py
- tests/distributed/test_pipeline_parallel.py
#- tests/distributed/test_pp_cudagraph.py
commands:
- set -x
- export VLLM_USE_V2_MODEL_RUNNER=1
- pytest -v -s distributed/test_pipeline_parallel.py -k "not ray and not Jamba"
# TODO: Uncomment once https://github.com/vllm-project/vllm/pull/35162 is merged.
#- pytest -v -s distributed/test_pp_cudagraph.py -k "not ray"
- label: Model Runner V2 Spec Decode
timeout_in_minutes: 30
working_dir: "/vllm-workspace/tests"
source_file_dependencies:
- vllm/v1/worker/gpu/
- vllm/v1/worker/gpu_worker.py
- tests/v1/spec_decode/test_max_len.py
- tests/v1/e2e/spec_decode/test_spec_decode.py
commands:
- set -x
- export VLLM_USE_V2_MODEL_RUNNER=1
- pytest -v -s v1/spec_decode/test_max_len.py -k "eagle or mtp"
- pytest -v -s v1/e2e/spec_decode/test_spec_decode.py -k "eagle or mtp"
.buildkite/test_areas/models_basic.yaml
View file @ 3fb4b5fa
...@@ -4,7 +4,6 @@ depends_on: ...@@ -4,7 +4,6 @@ depends_on:
steps: steps:
- label: Basic Models Tests (Initialization) - label: Basic Models Tests (Initialization)
timeout_in_minutes: 45 timeout_in_minutes: 45
mirror_hardwares: [amdexperimental]
torch_nightly: true torch_nightly: true
source_file_dependencies: source_file_dependencies:
- vllm/ - vllm/
...@@ -16,7 +15,6 @@ steps: ...@@ -16,7 +15,6 @@ steps:
- label: Basic Models Tests (Extra Initialization) %N - label: Basic Models Tests (Extra Initialization) %N
timeout_in_minutes: 45 timeout_in_minutes: 45
mirror_hardwares: [amdexperimental]
torch_nightly: true torch_nightly: true
source_file_dependencies: source_file_dependencies:
- vllm/model_executor/models/ - vllm/model_executor/models/
...@@ -38,6 +36,12 @@ steps: ...@@ -38,6 +36,12 @@ steps:
- tests/models/test_registry.py - tests/models/test_registry.py
commands: commands:
- pytest -v -s models/test_terratorch.py models/test_transformers.py models/test_registry.py - pytest -v -s models/test_terratorch.py models/test_transformers.py models/test_registry.py
mirror:
amd:
device: mi325_1
depends_on:
- image-build-amd
- label: Basic Models Test (Other CPU) # 5min - label: Basic Models Test (Other CPU) # 5min
depends_on: depends_on:
...@@ -61,7 +65,7 @@ steps: ...@@ -61,7 +65,7 @@ steps:
- pytest -v -s tests/models/test_transformers.py - pytest -v -s tests/models/test_transformers.py
- pytest -v -s tests/models/multimodal/processing/ - pytest -v -s tests/models/multimodal/processing/
- pytest -v -s tests/models/multimodal/test_mapping.py - pytest -v -s tests/models/multimodal/test_mapping.py
- python3 examples/offline_inference/basic/chat.py - python3 examples/basic/offline_inference/chat.py
- python3 examples/offline_inference/vision_language.py --model-type qwen2_5_vl - python3 examples/offline_inference/vision_language.py --model-type qwen2_5_vl
# Whisper needs spawn method to avoid deadlock # Whisper needs spawn method to avoid deadlock
- VLLM_WORKER_MULTIPROC_METHOD=spawn python3 examples/offline_inference/audio_language.py --model-type whisper - VLLM_WORKER_MULTIPROC_METHOD=spawn python3 examples/offline_inference/audio_language.py --model-type whisper
.buildkite/test_areas/models_language.yaml
View file @ 3fb4b5fa
...@@ -4,7 +4,6 @@ depends_on: ...@@ -4,7 +4,6 @@ depends_on:
steps: steps:
- label: Language Models Tests (Standard) - label: Language Models Tests (Standard)
timeout_in_minutes: 25 timeout_in_minutes: 25
mirror_hardwares: [amdexperimental]
torch_nightly: true torch_nightly: true
source_file_dependencies: source_file_dependencies:
- vllm/ - vllm/
...@@ -16,7 +15,6 @@ steps: ...@@ -16,7 +15,6 @@ steps:
- label: Language Models Tests (Extra Standard) %N - label: Language Models Tests (Extra Standard) %N
timeout_in_minutes: 45 timeout_in_minutes: 45
mirror_hardwares: [amdexperimental]
torch_nightly: true torch_nightly: true
source_file_dependencies: source_file_dependencies:
- vllm/model_executor/models/ - vllm/model_executor/models/
...@@ -32,7 +30,6 @@ steps: ...@@ -32,7 +30,6 @@ steps:
- label: Language Models Tests (Hybrid) %N - label: Language Models Tests (Hybrid) %N
timeout_in_minutes: 75 timeout_in_minutes: 75
mirror_hardwares: [amdexperimental]
torch_nightly: true torch_nightly: true
source_file_dependencies: source_file_dependencies:
- vllm/ - vllm/
...@@ -40,7 +37,7 @@ steps: ...@@ -40,7 +37,7 @@ steps:
commands: commands:
# Install fast path packages for testing against transformers # Install fast path packages for testing against transformers
# Note: also needed to run plamo2 model in vLLM # Note: also needed to run plamo2 model in vLLM
- uv pip install --system --no-build-isolation 'git+https://github.com/state-spaces/mamba@v2.2.5' - uv pip install --system --no-build-isolation 'git+https://github.com/state-spaces/mamba@v2.3.0'
- uv pip install --system --no-build-isolation 'git+https://github.com/Dao-AILab/causal-conv1d@v1.5.2' - uv pip install --system --no-build-isolation 'git+https://github.com/Dao-AILab/causal-conv1d@v1.5.2'
# Shard hybrid language model tests # Shard hybrid language model tests
- pytest -v -s models/language/generation -m hybrid_model --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --shard-id=$$BUILDKITE_PARALLEL_JOB - pytest -v -s models/language/generation -m hybrid_model --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --shard-id=$$BUILDKITE_PARALLEL_JOB
...@@ -48,7 +45,6 @@ steps: ...@@ -48,7 +45,6 @@ steps:
- label: Language Models Test (Extended Generation) # 80min - label: Language Models Test (Extended Generation) # 80min
timeout_in_minutes: 110 timeout_in_minutes: 110
mirror_hardwares: [amdexperimental]
optional: true optional: true
source_file_dependencies: source_file_dependencies:
- vllm/ - vllm/
...@@ -56,13 +52,21 @@ steps: ...@@ -56,13 +52,21 @@ steps:
commands: commands:
# Install fast path packages for testing against transformers # Install fast path packages for testing against transformers
# Note: also needed to run plamo2 model in vLLM # Note: also needed to run plamo2 model in vLLM
- uv pip install --system --no-build-isolation 'git+https://github.com/state-spaces/mamba@v2.2.5' - uv pip install --system --no-build-isolation 'git+https://github.com/state-spaces/mamba@v2.3.0'
- uv pip install --system --no-build-isolation 'git+https://github.com/Dao-AILab/causal-conv1d@v1.5.2' - uv pip install --system --no-build-isolation 'git+https://github.com/Dao-AILab/causal-conv1d@v1.5.2'
- pytest -v -s models/language/generation -m '(not core_model) and (not hybrid_model)' - pytest -v -s models/language/generation -m '(not core_model) and (not hybrid_model)'
mirror:
amd:
device: mi325_1
depends_on:
- image-build-amd
commands:
- uv pip install --system --no-build-isolation 'git+https://github.com/AndreasKaratzas/mamba@fix-rocm-7.0-warp-size-constexpr'
- uv pip install --system --no-build-isolation 'git+https://github.com/Dao-AILab/causal-conv1d@v1.5.2'
- pytest -v -s models/language/generation -m '(not core_model) and (not hybrid_model)'
- label: Language Models Test (PPL) - label: Language Models Test (PPL)
timeout_in_minutes: 110 timeout_in_minutes: 110
mirror_hardwares: [amdexperimental]
optional: true optional: true
source_file_dependencies: source_file_dependencies:
- vllm/ - vllm/
...@@ -72,17 +76,20 @@ steps: ...@@ -72,17 +76,20 @@ steps:
- label: Language Models Test (Extended Pooling) # 36min - label: Language Models Test (Extended Pooling) # 36min
timeout_in_minutes: 50 timeout_in_minutes: 50
mirror_hardwares: [amdexperimental]
optional: true optional: true
source_file_dependencies: source_file_dependencies:
- vllm/ - vllm/
- tests/models/language/pooling - tests/models/language/pooling
commands: commands:
- pytest -v -s models/language/pooling -m 'not core_model' - pytest -v -s models/language/pooling -m 'not core_model'
mirror:
amd:
device: mi325_1
depends_on:
- image-build-amd
- label: Language Models Test (MTEB) - label: Language Models Test (MTEB)
timeout_in_minutes: 110 timeout_in_minutes: 110
mirror_hardwares: [amdexperimental]
optional: true optional: true
source_file_dependencies: source_file_dependencies:
- vllm/ - vllm/
......
.buildkite/test_areas/models_multimodal.yaml
View file @ 3fb4b5fa
...@@ -2,16 +2,65 @@ group: Models - Multimodal ...@@ -2,16 +2,65 @@ group: Models - Multimodal
depends_on: depends_on:
- image-build - image-build
steps: steps:
- label: Multi-Modal Models (Standard) # 60min - label: "Multi-Modal Models (Standard) 1: qwen2"
timeout_in_minutes: 80 timeout_in_minutes: 45
source_file_dependencies: source_file_dependencies:
- vllm/ - vllm/
- tests/models/multimodal - tests/models/multimodal
commands: commands:
- pip install git+https://github.com/TIGER-AI-Lab/Mantis.git - pip install git+https://github.com/TIGER-AI-Lab/Mantis.git
- pip freeze | grep -E 'torch' - pytest -v -s models/multimodal/generation/test_common.py -m core_model -k "qwen2"
- pytest -v -s models/multimodal -m core_model --ignore models/multimodal/generation/test_whisper.py --ignore models/multimodal/processing - pytest -v -s models/multimodal/generation/test_ultravox.py -m core_model
mirror:
amd:
device: mi325_1
depends_on:
- image-build-amd
- label: "Multi-Modal Models (Standard) 2: qwen3 + gemma"
timeout_in_minutes: 45
source_file_dependencies:
- vllm/
- tests/models/multimodal
commands:
- pip install git+https://github.com/TIGER-AI-Lab/Mantis.git
- pytest -v -s models/multimodal/generation/test_common.py -m core_model -k "qwen3 or gemma"
- pytest -v -s models/multimodal/generation/test_qwen2_5_vl.py -m core_model
mirror:
amd:
device: mi325_1
depends_on:
- image-build-amd
- label: "Multi-Modal Models (Standard) 3: llava + qwen2_vl"
timeout_in_minutes: 45
source_file_dependencies:
- vllm/
- tests/models/multimodal
commands:
- pip install git+https://github.com/TIGER-AI-Lab/Mantis.git
- pytest -v -s models/multimodal/generation/test_common.py -m core_model -k "not qwen2 and not qwen3 and not gemma"
- pytest -v -s models/multimodal/generation/test_qwen2_vl.py -m core_model
mirror:
amd:
device: mi325_1
depends_on:
- image-build-amd
- label: "Multi-Modal Models (Standard) 4: other + whisper"
timeout_in_minutes: 45
source_file_dependencies:
- vllm/
- tests/models/multimodal
commands:
- pip install git+https://github.com/TIGER-AI-Lab/Mantis.git
- pytest -v -s models/multimodal -m core_model --ignore models/multimodal/generation/test_common.py --ignore models/multimodal/generation/test_ultravox.py --ignore models/multimodal/generation/test_qwen2_5_vl.py --ignore models/multimodal/generation/test_qwen2_vl.py --ignore models/multimodal/generation/test_whisper.py --ignore models/multimodal/processing
- cd .. && VLLM_WORKER_MULTIPROC_METHOD=spawn pytest -v -s tests/models/multimodal/generation/test_whisper.py -m core_model # Otherwise, mp_method="spawn" doesn't work - cd .. && VLLM_WORKER_MULTIPROC_METHOD=spawn pytest -v -s tests/models/multimodal/generation/test_whisper.py -m core_model # Otherwise, mp_method="spawn" doesn't work
mirror:
amd:
device: mi325_1
depends_on:
- image-build-amd
- label: Multi-Modal Processor Test (CPU) - label: Multi-Modal Processor Test (CPU)
depends_on: depends_on:
...@@ -20,6 +69,7 @@ steps: ...@@ -20,6 +69,7 @@ steps:
source_file_dependencies: source_file_dependencies:
- vllm/ - vllm/
- tests/models/multimodal - tests/models/multimodal
- tests/models/registry.py
device: cpu device: cpu
commands: commands:
- pip install git+https://github.com/TIGER-AI-Lab/Mantis.git - pip install git+https://github.com/TIGER-AI-Lab/Mantis.git
...@@ -30,6 +80,7 @@ steps: ...@@ -30,6 +80,7 @@ steps:
source_file_dependencies: source_file_dependencies:
- vllm/ - vllm/
- tests/models/multimodal - tests/models/multimodal
- tests/models/registry.py
commands: commands:
- pip install git+https://github.com/TIGER-AI-Lab/Mantis.git - pip install git+https://github.com/TIGER-AI-Lab/Mantis.git
- pytest -v -s models/multimodal/processing/test_tensor_schema.py - pytest -v -s models/multimodal/processing/test_tensor_schema.py
...@@ -52,6 +103,11 @@ steps: ...@@ -52,6 +103,11 @@ steps:
commands: commands:
- pip install git+https://github.com/TIGER-AI-Lab/Mantis.git - pip install git+https://github.com/TIGER-AI-Lab/Mantis.git
- pytest -v -s models/multimodal -m 'not core_model' --ignore models/multimodal/generation/test_common.py --ignore models/multimodal/processing - pytest -v -s models/multimodal -m 'not core_model' --ignore models/multimodal/generation/test_common.py --ignore models/multimodal/processing
mirror:
amd:
device: mi325_1
depends_on:
- image-build-amd
- label: Multi-Modal Models (Extended) 2 - label: Multi-Modal Models (Extended) 2
optional: true optional: true
...@@ -70,12 +126,3 @@ steps: ...@@ -70,12 +126,3 @@ steps:
commands: commands:
- pip install git+https://github.com/TIGER-AI-Lab/Mantis.git - pip install git+https://github.com/TIGER-AI-Lab/Mantis.git
- pytest -v -s models/multimodal/generation/test_common.py -m 'split(group=1) and not core_model' - pytest -v -s models/multimodal/generation/test_common.py -m 'split(group=1) and not core_model'
# This test is used only in PR development phase to test individual models and should never run on main
- label: Custom Models
optional: true
commands:
- echo 'Testing custom models...'
# PR authors can temporarily add commands below to test individual models
# e.g. pytest -v -s models/encoder_decoder/vision_language/test_mllama.py
# *To avoid merge conflicts, remember to REMOVE (not just comment out) them before merging the PR*
.buildkite/test_areas/plugins.yaml
View file @ 3fb4b5fa
...@@ -15,10 +15,17 @@ steps: ...@@ -15,10 +15,17 @@ steps:
- pytest -v -s plugins_tests/test_platform_plugins.py - pytest -v -s plugins_tests/test_platform_plugins.py
- pip uninstall vllm_add_dummy_platform -y - pip uninstall vllm_add_dummy_platform -y
# end platform plugin tests # end platform plugin tests
# begin io_processor plugins test, all the code in between uses the prithvi_io_processor plugin # begin io_processor plugins test
# test generic io_processor plugins functions
- pytest -v -s ./plugins_tests/test_io_processor_plugins.py
# test Terratorch io_processor plugins
- pip install -e ./plugins/prithvi_io_processor_plugin - pip install -e ./plugins/prithvi_io_processor_plugin
- pytest -v -s plugins_tests/test_io_processor_plugins.py - pytest -v -s plugins_tests/test_terratorch_io_processor_plugins.py
- pip uninstall prithvi_io_processor_plugin -y - pip uninstall prithvi_io_processor_plugin -y
# test bge_m3_sparse io_processor plugin
- pip install -e ./plugins/bge_m3_sparse_plugin
- pytest -v -s plugins_tests/test_bge_m3_sparse_io_processor_plugins.py
- pip uninstall bge_m3_sparse_plugin -y
# end io_processor plugins test # end io_processor plugins test
# begin stat_logger plugins test # begin stat_logger plugins test
- pip install -e ./plugins/vllm_add_dummy_stat_logger - pip install -e ./plugins/vllm_add_dummy_stat_logger
......
.buildkite/test_areas/ray_compat.yaml 0 → 100644
View file @ 3fb4b5fa
group: Ray Compatibility
depends_on:
- image-build
steps:
- label: Ray Dependency Compatibility Check
# Informational only — does not block the pipeline.
# If this fails, it means the PR introduces a dependency that
# conflicts with Ray's dependency constraints.
# See https://github.com/vllm-project/vllm/issues/33599
soft_fail: true
timeout_in_minutes: 10
source_file_dependencies:
- requirements/
- setup.py
commands:
- bash /vllm-workspace/.buildkite/scripts/check-ray-compatibility.sh
.buildkite/test_areas/samplers.yaml
View file @ 3fb4b5fa
...@@ -12,3 +12,10 @@ steps: ...@@ -12,3 +12,10 @@ steps:
commands: commands:
- pytest -v -s samplers - pytest -v -s samplers
- VLLM_USE_FLASHINFER_SAMPLER=1 pytest -v -s samplers - VLLM_USE_FLASHINFER_SAMPLER=1 pytest -v -s samplers
mirror:
amd:
device: mi325_1
depends_on:
- image-build-amd
commands:
- pytest -v -s samplers
.buildkite/test_areas/spec_decode.yaml 0 → 100644
View file @ 3fb4b5fa
group: Spec Decode
depends_on:
- image-build
steps:
- label: Spec Decode Eagle
timeout_in_minutes: 30
source_file_dependencies:
- vllm/v1/spec_decode/
- vllm/v1/worker/gpu/spec_decode/
- tests/v1/e2e/spec_decode/
commands:
- pytest -v -s v1/e2e/spec_decode -k "eagle_correctness"
- label: Spec Decode Speculators + MTP
timeout_in_minutes: 30
source_file_dependencies:
- vllm/v1/spec_decode/
- vllm/v1/worker/gpu/spec_decode/
- vllm/transformers_utils/configs/speculators/
- tests/v1/e2e/spec_decode/
commands:
- pytest -v -s v1/e2e/spec_decode -k "speculators or mtp_correctness"
- label: Spec Decode Ngram + Suffix
timeout_in_minutes: 30
source_file_dependencies:
- vllm/v1/spec_decode/
- vllm/v1/worker/gpu/spec_decode/
- tests/v1/e2e/spec_decode/
commands:
- pytest -v -s v1/e2e/spec_decode -k "ngram or suffix"
- label: Spec Decode Draft Model
timeout_in_minutes: 30
source_file_dependencies:
- vllm/v1/spec_decode/
- vllm/v1/worker/gpu/spec_decode/
- tests/v1/e2e/spec_decode/
commands:
- pytest -v -s v1/e2e/spec_decode -k "draft_model or no_sync or batch_inference"
.buildkite/test_areas/weight_loading.yaml
View file @ 3fb4b5fa
...@@ -13,13 +13,13 @@ steps: ...@@ -13,13 +13,13 @@ steps:
commands: commands:
- bash weight_loading/run_model_weight_loading_test.sh -c weight_loading/models.txt - bash weight_loading/run_model_weight_loading_test.sh -c weight_loading/models.txt
- label: Weight Loading Multiple GPU - Large Models # optional # - label: Weight Loading Multiple GPU - Large Models # optional
working_dir: "/vllm-workspace/tests" # working_dir: "/vllm-workspace/tests"
num_devices: 2 # num_devices: 2
device: a100 # device: a100
optional: true # optional: true
source_file_dependencies: # source_file_dependencies:
- vllm/ # - vllm/
- tests/weight_loading # - tests/weight_loading
commands: # commands:
- bash weight_loading/run_model_weight_loading_test.sh -c weight_loading/models-large.txt # - bash weight_loading/run_model_weight_loading_test.sh -c weight_loading/models-large.txt
.github/.bc-linter.yml deleted 100644 → 0
View file @ bcf25339
# doc: https://github.com/pytorch/test-infra/blob/main/tools/stronghold/docs/bc_linter_config.md
version: 1
paths:
# We temporarily disable globally, and will only enable with `annotations.include`
# include:
# - "vllm/v1/attetion/*.py"
# - "vllm/v1/core/*.py"
exclude:
- "**/*.py"
scan:
functions: true # check free functions and methods
classes: true # check classes/dataclasses
public_only: true # ignore names starting with "_" at any level
annotations:
include: # decorators that force‑include a symbol
- name: "bc_linter_include" # matched by simple name or dotted suffix
propagate_to_members: false # for classes, include methods/inner classes
exclude: # decorators that force‑exclude a symbol
- name: "bc_linter_skip" # matched by simple name or dotted suffix
propagate_to_members: true # for classes, exclude methods/inner classes
excluded_violations: [] # e.g. ["ParameterRenamed", "FieldTypeChanged"]
.github/CODEOWNERS
View file @ 3fb4b5fa
...@@ -2,45 +2,66 @@ ...@@ -2,45 +2,66 @@
# for more info about CODEOWNERS file # for more info about CODEOWNERS file
# This lists cover the "core" components of vLLM that require careful review # This lists cover the "core" components of vLLM that require careful review
/vllm/executor/executor_base.py @zhuohan123 @youkaichao @alexm-redhat @njhill @22quinn /vllm/compilation @zou3519 @youkaichao @ProExpertProg @BoyuanFeng
/vllm/model_executor/layers/attention @LucasWilkinson /vllm/distributed/kv_transfer @NickLucche @ApostaC @orozery
/vllm/lora @jeejeelee
/vllm/model_executor/layers/attention @LucasWilkinson @MatthewBonanni
/vllm/model_executor/layers/fused_moe @mgoin @pavanimajety /vllm/model_executor/layers/fused_moe @mgoin @pavanimajety
/vllm/model_executor/layers/quantization @mgoin @robertgshaw2-redhat @tlrmchlsmth @yewentao256 @pavanimajety /vllm/model_executor/layers/quantization @mgoin @robertgshaw2-redhat @tlrmchlsmth @yewentao256 @pavanimajety
/vllm/model_executor/layers/mamba @tdoublep /vllm/model_executor/layers/mamba @tdoublep
/vllm/model_executor/model_loader @22quinn /vllm/model_executor/model_loader @22quinn
/vllm/model_executor/layers/batch_invariant.py @yewentao256 /vllm/model_executor/layers/batch_invariant.py @yewentao256
/vllm/multimodal @DarkLight1337 @ywang96 @NickLucche @tjtanaa /vllm/multimodal @DarkLight1337 @ywang96 @NickLucche @tjtanaa
/vllm/vllm_flash_attn @LucasWilkinson /vllm/vllm_flash_attn @LucasWilkinson @MatthewBonanni
/vllm/lora @jeejeelee
/vllm/reasoning @aarnphm @chaunceyjiang
/vllm/entrypoints @aarnphm @chaunceyjiang
/vllm/tool_parsers @aarnphm @chaunceyjiang
/vllm/compilation @zou3519 @youkaichao @ProExpertProg
/vllm/distributed/kv_transfer @NickLucche @ApostaC @orozery
CMakeLists.txt @tlrmchlsmth @LucasWilkinson CMakeLists.txt @tlrmchlsmth @LucasWilkinson
# Any change to the VllmConfig changes can have a large user-facing impact, # Any change to the VllmConfig changes can have a large user-facing impact,
# so spam a lot of people # so spam a lot of people
/vllm/config @WoosukKwon @youkaichao @robertgshaw2-redhat @mgoin @tlrmchlsmth @houseroad @hmellor @yewentao256 @ProExpertProg /vllm/config @WoosukKwon @youkaichao @robertgshaw2-redhat @mgoin @tlrmchlsmth @houseroad @hmellor @yewentao256 @ProExpertProg
/vllm/config/cache.py @WoosukKwon @youkaichao @robertgshaw2-redhat @mgoin @tlrmchlsmth @houseroad @hmellor @yewentao256 @ProExpertProg @heheda12345 /vllm/config/cache.py @heheda12345
# Entrypoints
/vllm/entrypoints/anthropic @mgoin @DarkLight1337
/vllm/entrypoints/cli @hmellor @mgoin @DarkLight1337 @russellb
/vllm/entrypoints/mcp @heheda12345
/vllm/entrypoints/openai @aarnphm @chaunceyjiang @DarkLight1337 @russellb
/vllm/entrypoints/openai/realtime @njhill
/vllm/entrypoints/openai/speech_to_text @NickLucche
/vllm/entrypoints/pooling @noooop
/vllm/entrypoints/sagemaker @DarkLight1337
/vllm/entrypoints/serve @njhill
/vllm/entrypoints/*.py @njhill
/vllm/entrypoints/chat_utils.py @DarkLight1337
/vllm/entrypoints/llm.py @DarkLight1337
# Input/Output Processing
/vllm/sampling_params.py @njhill @NickLucche
/vllm/pooling_params.py @noooop @DarkLight1337
/vllm/tokenizers @DarkLight1337 @njhill
/vllm/renderers @DarkLight1337 @njhill
/vllm/reasoning @aarnphm @chaunceyjiang
/vllm/tool_parsers @aarnphm @chaunceyjiang
# vLLM V1 # vLLM V1
/vllm/v1/attention @LucasWilkinson /vllm/v1/attention @LucasWilkinson @MatthewBonanni
/vllm/v1/attention/backend.py @WoosukKwon @zhuohan123 @youkaichao @alexm-redhat @njhill /vllm/v1/attention/backend.py @WoosukKwon @zhuohan123 @youkaichao @alexm-redhat @njhill
/vllm/v1/attention/backends/mla @pavanimajety /vllm/v1/attention/backends/mla @pavanimajety
/vllm/v1/attention/backends/flashinfer.py @mgoin @pavanimajety /vllm/v1/attention/backends/flashinfer.py @mgoin @pavanimajety
/vllm/v1/attention/backends/triton_attn.py @tdoublep /vllm/v1/attention/backends/triton_attn.py @tdoublep
/vllm/v1/core @WoosukKwon @robertgshaw2-redhat @njhill @ywang96 @alexm-redhat @heheda12345 @ApostaC @orozery /vllm/v1/core @WoosukKwon @robertgshaw2-redhat @njhill @ywang96 @alexm-redhat @heheda12345 @ApostaC @orozery
/vllm/v1/sample @22quinn @houseroad @njhill /vllm/v1/sample @22quinn @houseroad @njhill
/vllm/v1/spec_decode @benchislett @luccafong /vllm/v1/spec_decode @benchislett @luccafong @MatthewBonanni
/vllm/v1/structured_output @mgoin @russellb @aarnphm @benchislett /vllm/v1/structured_output @mgoin @russellb @aarnphm @benchislett
/vllm/v1/kv_cache_interface.py @heheda12345 /vllm/v1/kv_cache_interface.py @heheda12345
/vllm/v1/kv_offload @ApostaC @orozery /vllm/v1/kv_offload @ApostaC @orozery
/vllm/v1/worker/gpu/kv_connector.py @orozery /vllm/v1/engine @njhill
/vllm/v1/worker/kv_connector_model_runner_mixin.py @orozery /vllm/v1/executor @njhill
/vllm/v1/worker @njhill
/vllm/v1/worker/kv_connector_model_runner_mixin.py @orozery @NickLucche
# Model runner V2 # Model runner V2
/vllm/v1/worker/gpu @WoosukKwon /vllm/v1/worker/gpu @WoosukKwon @njhill
/vllm/v1/worker/gpu/kv_connector.py @orozery
# Test ownership # Test ownership
/.buildkite/lm-eval-harness @mgoin /.buildkite/lm-eval-harness @mgoin
...@@ -115,8 +136,8 @@ mkdocs.yaml @hmellor ...@@ -115,8 +136,8 @@ mkdocs.yaml @hmellor
/vllm/model_executor/models/mixtral*.py @patrickvonplaten /vllm/model_executor/models/mixtral*.py @patrickvonplaten
/vllm/model_executor/models/voxtral*.py @patrickvonplaten /vllm/model_executor/models/voxtral*.py @patrickvonplaten
/vllm/model_executor/models/pixtral*.py @patrickvonplaten /vllm/model_executor/models/pixtral*.py @patrickvonplaten
/vllm/tokenizers/mistral.py @patrickvonplaten
/vllm/transformers_utils/configs/mistral.py @patrickvonplaten /vllm/transformers_utils/configs/mistral.py @patrickvonplaten
/vllm/transformers_utils/tokenizers/mistral.py @patrickvonplaten
# Kernels # Kernels
/vllm/v1/attention/ops/chunked_prefill_paged_decode.py @tdoublep /vllm/v1/attention/ops/chunked_prefill_paged_decode.py @tdoublep
...@@ -152,9 +173,7 @@ mkdocs.yaml @hmellor ...@@ -152,9 +173,7 @@ mkdocs.yaml @hmellor
/examples/pooling @noooop /examples/pooling @noooop
/tests/models/*/pooling* @noooop /tests/models/*/pooling* @noooop
/tests/entrypoints/pooling @noooop /tests/entrypoints/pooling @noooop
/vllm/entrypoints/pooling @noooop
/vllm/config/pooler.py @noooop /vllm/config/pooler.py @noooop
/vllm/pooling_params.py @noooop
/vllm/model_executor/layers/pooler @noooop /vllm/model_executor/layers/pooler @noooop
# Security guide and policies # Security guide and policies
......
.github/mergify.yml
View file @ 3fb4b5fa
...@@ -3,6 +3,7 @@ pull_request_rules: ...@@ -3,6 +3,7 @@ pull_request_rules:
description: Automatically apply documentation label description: Automatically apply documentation label
conditions: conditions:
- label != stale - label != stale
- -closed
- or: - or:
- files~=^[^/]+\.md$ - files~=^[^/]+\.md$
- files~=^docs/ - files~=^docs/
...@@ -26,7 +27,7 @@ pull_request_rules: ...@@ -26,7 +27,7 @@ pull_request_rules:
Hi @{{author}}, the pre-commit checks have failed. Please run: Hi @{{author}}, the pre-commit checks have failed. Please run:
```bash ```bash
uv pip install pre-commit uv pip install pre-commit>=4.5.1
pre-commit install pre-commit install
pre-commit run --all-files pre-commit run --all-files
``` ```
...@@ -37,15 +38,13 @@ pull_request_rules: ...@@ -37,15 +38,13 @@ pull_request_rules:
> [!TIP] > [!TIP]
> <details> > <details>
> <summary>Is <code>mypy</code> or <code>markdownlint</code> failing?</summary> > <summary>Is <code>mypy</code> failing?</summary>
> <br/> > <br/>
> <code>mypy</code> and <code>markdownlint</code> are run differently in CI. If the failure is related to either of these checks, please use the following commands to run them locally: > <code>mypy</code> is run differently in CI. If the failure is related to this check, please use the following command to run it locally:
> >
> ```bash > ```bash
> # For mypy (substitute "3.10" with the failing version if needed) > # For mypy (substitute "3.10" with the failing version if needed)
> pre-commit run --hook-stage manual mypy-3.10 > pre-commit run --hook-stage manual mypy-3.10
> # For markdownlint
> pre-commit run --hook-stage manual markdownlint
> ``` > ```
> </details> > </details>
...@@ -259,8 +258,7 @@ pull_request_rules: ...@@ -259,8 +258,7 @@ pull_request_rules:
- files=benchmarks/run_structured_output_benchmark.sh - files=benchmarks/run_structured_output_benchmark.sh
- files=docs/features/structured_outputs.md - files=docs/features/structured_outputs.md
- files=examples/offline_inference/structured_outputs.py - files=examples/offline_inference/structured_outputs.py
- files=examples/online_serving/openai_chat_completion_structured_outputs.py - files=examples/online_serving/structured_outputs/structured_outputs.py
- files=examples/online_serving/openai_chat_completion_structured_outputs_with_reasoning.py
- files~=^tests/v1/structured_output/ - files~=^tests/v1/structured_output/
- files=tests/v1/entrypoints/llm/test_struct_output_generate.py - files=tests/v1/entrypoints/llm/test_struct_output_generate.py
- files~=^vllm/v1/structured_output/ - files~=^vllm/v1/structured_output/
...@@ -336,7 +334,7 @@ pull_request_rules: ...@@ -336,7 +334,7 @@ pull_request_rules:
- or: - or:
- files~=^tests/tool_use/ - files~=^tests/tool_use/
- files~=^tests/entrypoints/openai/tool_parsers/ - files~=^tests/entrypoints/openai/tool_parsers/
- files=tests/entrypoints/openai/test_chat_with_tool_reasoning.py - files=tests/entrypoints/openai/chat_completion/test_chat_with_tool_reasoning.py
- files~=^vllm/entrypoints/openai/tool_parsers/ - files~=^vllm/entrypoints/openai/tool_parsers/
- files=docs/features/tool_calling.md - files=docs/features/tool_calling.md
- files~=^examples/tool_chat_* - files~=^examples/tool_chat_*
......
.github/workflows/bc-lint.yml deleted 100644 → 0
View file @ bcf25339
name: BC Lint
on:
pull_request:
types:
- opened
- synchronize
- reopened
- labeled
- unlabeled
jobs:
bc_lint:
if: github.repository_owner == 'vllm-project'
runs-on: ubuntu-latest
steps:
- name: Run BC Lint Action
uses: pytorch/test-infra/.github/actions/bc-lint@main
with:
repo: ${{ github.event.pull_request.head.repo.full_name }}
base_sha: ${{ github.event.pull_request.base.sha }}
head_sha: ${{ github.event.pull_request.head.sha }}
suppression: ${{ contains(github.event.pull_request.labels.*.name, 'suppress-bc-linter') }}
docs_link: 'https://github.com/pytorch/test-infra/wiki/BC-Linter'
config_dir: .github
concurrency:
group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.sha }}
cancel-in-progress: true
.github/workflows/cleanup_pr_body.yml
View file @ 3fb4b5fa
...@@ -19,6 +19,7 @@ jobs: ...@@ -19,6 +19,7 @@ jobs:
uses: actions/setup-python@83679a892e2d95755f2dac6acb0bfd1e9ac5d548 # v6.1.0 uses: actions/setup-python@83679a892e2d95755f2dac6acb0bfd1e9ac5d548 # v6.1.0
with: with:
python-version: '3.12' python-version: '3.12'
cache: 'pip'
- name: Install Python dependencies - name: Install Python dependencies
run: | run: |
......
.github/workflows/macos-smoke-test.yml
View file @ 3fb4b5fa
...@@ -6,6 +6,9 @@ on: ...@@ -6,6 +6,9 @@ on:
- main - main
workflow_dispatch: # Manual trigger workflow_dispatch: # Manual trigger
permissions:
contents: read
jobs: jobs:
macos-m1-smoke-test: macos-m1-smoke-test:
runs-on: macos-latest runs-on: macos-latest
......
.gitignore
View file @ 3fb4b5fa
...@@ -3,6 +3,8 @@ ...@@ -3,6 +3,8 @@
# vllm-flash-attn built from source # vllm-flash-attn built from source
vllm/vllm_flash_attn/* vllm/vllm_flash_attn/*
!vllm/vllm_flash_attn/__init__.py
!vllm/vllm_flash_attn/flash_attn_interface.py
# OpenAI triton kernels copied from source # OpenAI triton kernels copied from source
vllm/third_party/triton_kernels/* vllm/third_party/triton_kernels/*
...@@ -187,11 +189,9 @@ cython_debug/ ...@@ -187,11 +189,9 @@ cython_debug/
.vscode/ .vscode/
# Claude # Claude
CLAUDE.md
.claude/ .claude/
# Codex # Codex
AGENTS.md
.codex/ .codex/
# Cursor # Cursor
...@@ -238,3 +238,6 @@ ep_kernels_workspace/ ...@@ -238,3 +238,6 @@ ep_kernels_workspace/
vllm/grpc/vllm_engine_pb2.py vllm/grpc/vllm_engine_pb2.py
vllm/grpc/vllm_engine_pb2_grpc.py vllm/grpc/vllm_engine_pb2_grpc.py
vllm/grpc/vllm_engine_pb2.pyi vllm/grpc/vllm_engine_pb2.pyi
# Ignore generated cpu headers
csrc/cpu/cpu_attn_dispatch_generated.h
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