@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 2f2cdc745a
Fork 0

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 16, 05:45 UTC

[MISC][XPU] quick fix for XPU CI (#10859)

Signed-off-by: yan ma <yan.ma@intel.com>

Yan Ma committed Dec 4, 2024 at 01:16 UTC 2f2cdc745a7a569637c58cfd5f6789c1d0741c84
1 file changed +4 -3
.buildkite/run-xpu-test.sh
+4 -3
@@ -13,6 +13,7 @@ trap remove_docker_container EXIT
13 remove_docker_container
14
15 # Run the image and test offline inference/tensor parallel
16 -docker run -it -d --name xpu-test --device /dev/dri -v /dev/dri/by-path:/dev/dri/by-path xpu-test /bin/bash
17 -docker exec xpu-test bash -c "python3 examples/offline_inference.py"
18 -docker exec xpu-test bash -c "python3 examples/offline_inference_cli.py -tp 2"
16 +docker run --name xpu-test --device /dev/dri -v /dev/dri/by-path:/dev/dri/by-path --entrypoint="" xpu-test sh -c '
17 + python3 examples/offline_inference.py
18 + python3 examples/offline_inference_cli.py -tp 2
19 +'