Enable Intel ARC gpu test for vllm openvino.

Signed-off-by: senhui2intel <[email protected]>

Author: senhui2intel

comps/llms/text-generation/vllm/langchain/dependency/Dockerfile.openvino_arc

@@ -0,0 +1,43 @@
+# The vLLM Dockerfile is used to construct vLLM image that can be directly used
+# to run the OpenAI compatible server.
+# Based on https://github.com/vllm-project/vllm/blob/main/Dockerfile.openvino
+# add Intel ARC support package
+
+FROM ubuntu:22.04 AS dev
+
+RUN apt-get update -y && \
+    apt-get install -y \
+        git python3-pip \
+        ffmpeg libsm6 libxext6 libgl1 \
+        gpg-agent wget
+
+RUN wget -qO - https://repositories.intel.com/gpu/intel-graphics.key | gpg --yes --dearmor --output /usr/share/keyrings/intel-graphics.gpg && \
+    echo "deb [arch=amd64 signed-by=/usr/share/keyrings/intel-graphics.gpg] https://repositories.intel.com/gpu/ubuntu jammy/lts/2350 unified" | \
+        tee /etc/apt/sources.list.d/intel-gpu-jammy.list &&\
+    apt update -y &&\
+    apt install -y \
+        intel-opencl-icd intel-level-zero-gpu level-zero \
+        intel-media-va-driver-non-free libmfx1 libmfxgen1 libvpl2 \
+        libegl-mesa0 libegl1-mesa libegl1-mesa-dev libgbm1 libgl1-mesa-dev libgl1-mesa-dri \
+        libglapi-mesa libgles2-mesa-dev libglx-mesa0 libigdgmm12 libxatracker2 mesa-va-drivers \
+        mesa-vdpau-drivers mesa-vulkan-drivers va-driver-all vainfo hwinfo clinfo
+
+WORKDIR /workspace
+
+RUN git clone -b v0.6.3.post1 https://github.com/vllm-project/vllm.git
+
+#ARG GIT_REPO_CHECK=0
+#RUN --mount=type=bind,source=.git,target=.git \
+#    if [ "$GIT_REPO_CHECK" != 0 ]; then bash tools/check_repo.sh ; fi
+
+# install build requirements
+RUN PIP_EXTRA_INDEX_URL="https://download.pytorch.org/whl/cpu" python3 -m pip install -r /workspace/vllm/requirements-build.txt
+# build vLLM with OpenVINO backend
+RUN PIP_EXTRA_INDEX_URL="https://download.pytorch.org/whl/cpu" VLLM_TARGET_DEVICE="openvino" python3 -m pip install /workspace/vllm/
+
+#COPY examples/ /workspace/vllm/examples
+#COPY benchmarks/ /workspace/vllm/benchmarks
+
+
+CMD ["/bin/bash"]
+

tests/llms/test_llms_text-generation_vllm_langchain_openvino_on_intel_arc.sh

@@ -5,49 +5,28 @@
 set -x
 
 WORKPATH="$( cd "$( dirname "$0" )" && pwd )"
+DOCKER_FILE="$WORKPATH"/../../comps/llms/text-generation/vllm/langchain/dependency/Dockerfile.openvino_arc
 
 # Define variables
 port=5033
 RENDER_GROUP_ID=110
-HF_MODEL_FIR=$HOME/hf_model
 DOCKER_IMAGE="vllm-openvino:comps"
 CONTAINER_NAME="test-comps-vllm-openvino-container"
+HF_CACHE_DIR=$HOME/.cache/huggingface
 
 function build_container() {
-    cd $WORKPATH
-    git clone https://github.com/vllm-project/vllm.git vllm-openvino
-    cd ./vllm-openvino
-
-    git reset --hard 067e77f9a87c3466fce41c8fe8710fddc69ec26c # resolve circular import issue
-
-    # Add ARC drive to dockerfile
-    sed -i '9r /dev/stdin' Dockerfile.openvino << EndOfMessage
-RUN apt-get install -y gpg-agent wget
-RUN wget -qO - https://repositories.intel.com/gpu/intel-graphics.key | gpg --yes --dearmor --output /usr/share/keyrings/intel-graphics.gpg && \\
-    echo "deb [arch=amd64 signed-by=/usr/share/keyrings/intel-graphics.gpg] https://repositories.intel.com/gpu/ubuntu jammy/lts/2350 unified" | \\
-        tee /etc/apt/sources.list.d/intel-gpu-jammy.list && \\
-    apt-get update -y && \\
-    apt-get install -y \\
-        intel-opencl-icd intel-level-zero-gpu level-zero \\
-        intel-media-va-driver-non-free libmfx1 libmfxgen1 libvpl2 \\
-        libegl-mesa0 libegl1-mesa libegl1-mesa-dev libgbm1 libgl1-mesa-dev libgl1-mesa-dri \\
-        libglapi-mesa libgles2-mesa-dev libglx-mesa0 libigdgmm12 libxatracker2 mesa-va-drivers \\
-        mesa-vdpau-drivers mesa-vulkan-drivers va-driver-all vainfo hwinfo clinfo
-EndOfMessage
-
     docker build --no-cache -t $DOCKER_IMAGE \
-      -f Dockerfile.openvino \
+      -f $DOCKER_FILE \
       . \
       --build-arg https_proxy=$https_proxy \
       --build-arg http_proxy=$http_proxy
+
     if [ $? -ne 0 ]; then
         echo "vllm-openvino built fail"
         exit 1
     else
         echo "vllm-openvino built successful"
     fi
-    cd $WORKPATH
-    rm -rf vllm-openvino
 }
 
 # Function to start Docker container
@@ -58,14 +37,14 @@ start_container() {
       --ipc=host \
       -e HTTPS_PROXY=$https_proxy \
       -e HTTP_PROXY=$https_proxy \
-      -v $HF_MODEL_FIR:/hf_model \
+      -v $HF_CACHE_DIR:/root/.cache/huggingface \
       --device=/dev/dri:/dev/dri \
-      --group-add $RENDER_GROUP_ID
+      --group-add $RENDER_GROUP_ID \
       vllm-openvino:comps /bin/bash -c "\
         export VLLM_OPENVINO_DEVICE=GPU && \
         export VLLM_OPENVINO_ENABLE_QUANTIZED_WEIGHTS=ON && \
         python3 -m vllm.entrypoints.openai.api_server \
-          --model /hf_model/neural-chat-7b-v3-3 \
+          --model Intel/neural-chat-7b-v3-3 \
           --host 0.0.0.0 \
           --port $port \
           --max_model_len 8192"
@@ -131,8 +110,7 @@ function test_api_endpoint {
 # Main function
 main() {
 
-    # use local image to skip slow network connection
-    # build_container
+    build_container
     start_container
 
     # Sleep to allow the container to start up fully