A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 08:30 UTC
[CI/Build] Fix V1 flag being set in entrypoints tests (#18598)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Cyrus Leung committed
May 23, 2025 at 20:51 UTC
6dd51c7ef11ff06ce589c41ae0c3aef30f3f13b8
1 file changed
+3
-2
.buildkite/test-pipeline.yaml
+3
-2
@@ -125,9 +125,8 @@ steps:
125
- pytest -v -s entrypoints/llm/test_generate.py # it needs a clean process
126
- pytest -v -s entrypoints/llm/test_generate_multiple_loras.py # it needs a clean process
127
- VLLM_USE_V1=0 pytest -v -s entrypoints/llm/test_guided_generate.py # it needs a clean process
128
- - pytest -v -s entrypoints/openai --ignore=entrypoints/openai/test_oot_registration.py --ignore=entrypoints/openai/test_chat_with_tool_reasoning.py --ignore=entrypoints/openai/correctness/
128
+ - 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/
129
- pytest -v -s entrypoints/test_chat_utils.py
130
- - pytest -v -s entrypoints/openai/test_tensorizer_entrypoint.py
130
- VLLM_USE_V1=0 pytest -v -s entrypoints/offline_mode # Needs to avoid interference with other tests
131
132
- label: Distributed Tests (4 GPUs) # 10min
@@ -390,10 +389,12 @@ steps:
389
source_file_dependencies:
390
- vllm/model_executor/model_loader
391
- tests/tensorizer_loader
392
+ - tests/entrypoints/openai/test_tensorizer_entrypoint.py
393
commands:
394
- apt-get update && apt-get install -y curl libsodium23
395
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
396
- pytest -v -s tensorizer_loader
397
+ - pytest -v -s entrypoints/openai/test_tensorizer_entrypoint.py
398
399
- label: Benchmarks # 9min
400
mirror_hardwares: [amdexperimental, amdproduction]