From 946aadb4a0e07bf735b0f0145230c59002dc5089 Mon Sep 17 00:00:00 2001 From: Michael Goin Date: Tue, 15 Jul 2025 11:44:18 +0900 Subject: [PATCH] [CI/Build] Split Entrypoints Test into LLM and API Server (#20945) Signed-off-by: mgoin --- .buildkite/test-pipeline.yaml | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) diff --git a/.buildkite/test-pipeline.yaml b/.buildkite/test-pipeline.yaml index 4440187c3..dd723cb62 100644 --- a/.buildkite/test-pipeline.yaml +++ b/.buildkite/test-pipeline.yaml @@ -117,7 +117,7 @@ steps: commands: - pytest -v -s core -- label: Entrypoints Test # 40min +- label: Entrypoints Test (LLM) # 40min mirror_hardwares: [amdexperimental] working_dir: "/vllm-workspace/tests" fast_check: true @@ -125,8 +125,6 @@ steps: source_file_dependencies: - vllm/ - tests/entrypoints/llm - - tests/entrypoints/openai - - tests/entrypoints/test_chat_utils - tests/entrypoints/offline_mode commands: - export VLLM_WORKER_MULTIPROC_METHOD=spawn @@ -135,9 +133,21 @@ steps: - pytest -v -s entrypoints/llm/test_generate.py # it needs a clean process - pytest -v -s entrypoints/llm/test_generate_multiple_loras.py # it needs a clean process - VLLM_USE_V1=0 pytest -v -s entrypoints/llm/test_guided_generate.py # it needs a clean process + - VLLM_USE_V1=0 pytest -v -s entrypoints/offline_mode # Needs to avoid interference with other tests + +- label: Entrypoints Test (API Server) # 40min + mirror_hardwares: [amdexperimental] + working_dir: "/vllm-workspace/tests" + fast_check: true + torch_nightly: true + source_file_dependencies: + - vllm/ + - tests/entrypoints/openai + - tests/entrypoints/test_chat_utils + commands: + - export VLLM_WORKER_MULTIPROC_METHOD=spawn - pytest -v -s entrypoints/openai --ignore=entrypoints/openai/test_chat_with_tool_reasoning.py --ignore=entrypoints/openai/test_oot_registration.py --ignore=entrypoints/openai/test_tensorizer_entrypoint.py --ignore=entrypoints/openai/correctness/ - pytest -v -s entrypoints/test_chat_utils.py - - VLLM_USE_V1=0 pytest -v -s entrypoints/offline_mode # Needs to avoid interference with other tests - label: Distributed Tests (4 GPUs) # 10min mirror_hardwares: [amdexperimental]