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 15, 18:30 UTC
[CI][Intel GPU] update XPU dockerfile and CI script (#15109)
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
Kunshang Ji committed
Mar 19, 2025 at 01:29 UTC
68cf1601d3ccac7b7a661390d972a2469a7b4c61
2 files changed
+8
-13
.buildkite/run-xpu-test.sh
+5
-4
@@ -12,10 +12,11 @@ docker build -t ${image_name} -f Dockerfile.xpu .
12
13
# Setup cleanup
14
remove_docker_container() {
15
- docker rm -f "${container_name}" || docker image rm -f "${image_name}" || true;
15
+ docker rm -f "${container_name}" || true;
16
+ docker image rm -f "${image_name}" || true;
17
+ docker system prune -f || true;
18
}
19
trap remove_docker_container EXIT
18
-remove_docker_container
20
21
# Run the image and test offline inference/tensor parallel
22
docker run \
@@ -25,6 +26,6 @@ docker run \
26
--name "${container_name}" \
27
"${image_name}" \
28
sh -c '
28
- python3 examples/offline_inference/basic/generate.py --model facebook/opt-125m
29
- python3 examples/offline_inference/basic/generate.py --model facebook/opt-125m -tp 2
29
+ VLLM_USE_V1=0 python3 examples/offline_inference/basic/generate.py --model facebook/opt-125m
30
+ VLLM_USE_V1=0 python3 examples/offline_inference/basic/generate.py --model facebook/opt-125m -tp 2
31
'
Dockerfile.xpu
+3
-9
@@ -1,11 +1,7 @@
1
-FROM intel/deep-learning-essentials:2025.0.1-0-devel-ubuntu22.04 AS vllm-base
1
+# oneapi 2025.0.2 docker base image use rolling 2448 package. https://dgpu-docs.intel.com/releases/packages.html?release=Rolling+2448.13&os=Ubuntu+22.04, and we don't need install driver manually.
2
+FROM intel/deep-learning-essentials:2025.0.2-0-devel-ubuntu22.04 AS vllm-base
3
3
-RUN wget -O- https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB | gpg --dearmor | tee /usr/share/keyrings/intel-oneapi-archive-keyring.gpg > /dev/null && \
4
- echo "deb [signed-by=/usr/share/keyrings/intel-oneapi-archive-keyring.gpg] https://apt.repos.intel.com/oneapi all main " | tee /etc/apt/sources.list.d/oneAPI.list && \
5
- chmod 644 /usr/share/keyrings/intel-oneapi-archive-keyring.gpg && \
6
- wget -O- https://repositories.intel.com/graphics/intel-graphics.key | gpg --dearmor | tee /usr/share/keyrings/intel-graphics.gpg > /dev/null && \
7
- echo "deb [arch=amd64,i386 signed-by=/usr/share/keyrings/intel-graphics.gpg] https://repositories.intel.com/graphics/ubuntu jammy arc" | tee /etc/apt/sources.list.d/intel.gpu.jammy.list && \
8
- chmod 644 /usr/share/keyrings/intel-graphics.gpg
4
+RUN rm /etc/apt/sources.list.d/intel-graphics.list
5
6
RUN apt-get update -y && \
7
apt-get install -y --no-install-recommends --fix-missing \
@@ -21,8 +17,6 @@ RUN apt-get update -y && \
17
python3 \
18
python3-dev \
19
python3-pip \
24
- libze-intel-gpu-dev \
25
- libze-intel-gpu1 \
20
wget
21
22
WORKDIR /workspace/vllm