diff --git a/.buildkite/test_areas/engine.yaml b/.buildkite/test_areas/engine.yaml index cf0f028255..c8b2d66a41 100644 --- a/.buildkite/test_areas/engine.yaml +++ b/.buildkite/test_areas/engine.yaml @@ -7,7 +7,17 @@ steps: timeout_in_minutes: 15 device: h200_18gb source_file_dependencies: - - vllm/ + - vllm/compilation/ + - vllm/config/ + - vllm/engine/ + - vllm/entrypoints/logger.py + - vllm/envs.py + - vllm/logger.py + - vllm/logging_utils/ + - vllm/platforms/ + - vllm/sequence.py + - vllm/triton_utils/ + - vllm/utils/ - tests/engine - tests/test_sequence - tests/test_config @@ -52,8 +62,24 @@ steps: optional: true num_devices: 2 source_file_dependencies: - - vllm/ - - tests/v1/e2e + - vllm/compilation/ + - vllm/config/ + - vllm/distributed/ + - vllm/engine/ + - vllm/envs.py + - vllm/forward_context.py + - vllm/inputs/ + - vllm/logger.py + - vllm/logging_utils/ + - vllm/model_executor/ + - vllm/multimodal/ + - vllm/platforms/ + - vllm/sampling_params.py + - vllm/transformers_utils/ + - vllm/triton_utils/ + - vllm/utils/ + - vllm/v1/ + - tests/v1/e2e/spec_decode commands: # Only run tests that need exactly 2 GPUs - pytest -v -s v1/e2e/spec_decode/test_spec_decode.py -k "tensor_parallelism" @@ -64,8 +90,24 @@ steps: optional: true num_devices: 4 source_file_dependencies: - - vllm/ - - tests/v1/e2e + - vllm/compilation/ + - vllm/config/ + - vllm/distributed/ + - vllm/engine/ + - vllm/envs.py + - vllm/forward_context.py + - vllm/inputs/ + - vllm/logger.py + - vllm/logging_utils/ + - vllm/model_executor/ + - vllm/multimodal/ + - vllm/platforms/ + - vllm/sampling_params.py + - vllm/transformers_utils/ + - vllm/triton_utils/ + - vllm/utils/ + - vllm/v1/ + - tests/v1/e2e/spec_decode commands: # Only run tests that need 4 GPUs - pytest -v -s v1/e2e/spec_decode/test_spec_decode.py -k "eagle_correctness_heavy"