biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[CI][Intel GPU] update XPU dockerfile and CI script (#15109)

Browse Source 
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
This commit is contained in:
Kunshang Ji
2025-03-19 01:29:25 -07:00
committed by GitHub
parent 61f412187d
commit 68cf1601d3
2 changed files with 8 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
.buildkite/run-xpu-test.sh
View File

@@ -12,10 +12,11 @@ docker build -t ${image_name} -f Dockerfile.xpu .
# Setup cleanup
remove_docker_container() {
docker rm -f "${container_name}" || docker image rm -f "${image_name}" || true;
docker rm -f "${container_name}" || true;
docker image rm -f "${image_name}" || true;
docker system prune -f || true;
}
trap remove_docker_container EXIT
remove_docker_container
# Run the image and test offline inference/tensor parallel
docker run \
@@ -25,6 +26,6 @@ docker run \
--name "${container_name}" \
"${image_name}" \
sh -c '
python3 examples/offline_inference/basic/generate.py --model facebook/opt-125m
python3 examples/offline_inference/basic/generate.py --model facebook/opt-125m -tp 2
VLLM_USE_V1=0 python3 examples/offline_inference/basic/generate.py --model facebook/opt-125m
VLLM_USE_V1=0 python3 examples/offline_inference/basic/generate.py --model facebook/opt-125m -tp 2
'