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

[Misc][XPU] Avoid torch compile for XPU platform (#10747)

Browse Source 
Signed-off-by: yan ma <yan.ma@intel.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
This commit is contained in:
Yan Ma
2024-12-03 01:53:55 +08:00
committed by GitHub
parent b45f0d7946
commit 519cc6ca12
2 changed files with 8 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
.buildkite/run-xpu-test.sh
View File

@@ -12,5 +12,7 @@ remove_docker_container() { docker rm -f xpu-test || true; }
trap remove_docker_container EXIT
remove_docker_container
# Run the image and launch offline inference
docker run --network host --name xpu-test --device /dev/dri -v /dev/dri/by-path:/dev/dri/by-path --entrypoint="" xpu-test python3 examples/offline_inference.py
# Run the image and test offline inference/tensor parallel
docker run -it -d --name xpu-test --device /dev/dri -v /dev/dri/by-path:/dev/dri/by-path xpu-test /bin/bash
docker exec xpu-test bash -c "python3 examples/offline_inference.py"
docker exec xpu-test bash -c "python3 examples/offline_inference_cli.py -tp 2"