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
+'