wassname/vllm
1
0
Fork 0
mirror of https://github.com/wassname/vllm.git synced 2026-08-08 11:29:04 +08:00
Code Issues Packages Projects Releases Wiki Activity

[CI/Build] Reducing CPU CI execution time (#5241)

Browse Source
This commit is contained in:
Li, Jiang
2024-06-04 10:26:40 -07:00
committed by GitHub
parent 9ba093b4f4
commit 45c35f0d58
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.buildkite/run-cpu-test.sh
+1 -1
View File
@@ -11,7 +11,7 @@ trap remove_docker_container EXIT
remove_docker_container
# Run the image
docker run -itd -v ~/.cache/huggingface:/root/.cache/huggingface --network host -e HF_TOKEN --env VLLM_CPU_KVCACHE_SPACE=4 --name cpu-test cpu-test
docker run -itd -v ~/.cache/huggingface:/root/.cache/huggingface --cpuset-cpus=48-95 --cpuset-mems=1 --network host -e HF_TOKEN --env VLLM_CPU_KVCACHE_SPACE=4 --name cpu-test cpu-test
# offline inference
docker exec cpu-test bash -c "python3 examples/offline_inference.py"