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, 21:00 UTC
[CI] Disable spawn when running V1 Test (#14345)
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
Thomas Parnell committed
Mar 6, 2025 at 22:52 UTC
8ca2b21c989cc5658353f240318dab489fba95c2
1 file changed
-1
.buildkite/test-pipeline.yaml
-1
@@ -200,7 +200,6 @@ steps:
200
- tests/v1
201
commands:
202
# split the test to avoid interference
203
- - export VLLM_WORKER_MULTIPROC_METHOD=spawn
203
- VLLM_USE_V1=1 pytest -v -s v1/core
204
- VLLM_USE_V1=1 pytest -v -s v1/engine
205
- VLLM_USE_V1=1 pytest -v -s v1/sample