test prtest image update

.github/workflows/pr_ete_test.yml

@@ -33,7 +33,7 @@ jobs:
     env:
       REPORT_DIR: /nvme/qa_test_models/test-reports
     container:
-      image: nvcr.io/nvidia/tritonserver:24.03-py3
+      image: nvidia/cuda:12.4.1-devel-ubuntu22.04
       options: "--gpus=all --ipc=host --user root -e PIP_CACHE_DIR=/root/.cache/pip --pull never"
       volumes:
         - /nvme/share_data/github-actions/pip-cache:/root/.cache/pip
@@ -43,36 +43,40 @@ jobs:
     steps:
       - name: Setup systems
         run: |
-          rm /etc/apt/sources.list.d/cuda*.list
-          apt-get update && apt-get install -y --no-install-recommends rapidjson-dev \
-              libgoogle-glog-dev libgl1 openjdk-8-jre-headless
-          rm -rf /var/lib/apt/lists/*
+          rm /etc/apt/sources.list.d/cuda*.list && apt-get update -y && apt-get install -y software-properties-common wget vim &&\
+          add-apt-repository ppa:deadsnakes/ppa -y && apt-get update -y && apt-get install -y --no-install-recommends \
+          rapidjson-dev libgoogle-glog-dev gdb python3.10 python3.10-dev python3.10-venv \
+          && apt-get clean -y && rm -rf /var/lib/apt/lists/* && cd /opt && python3 -m venv py3
+          echo "PATH=/opt/py3/bin:$PATH" >> "$GITHUB_ENV"
       - name: Clone repository
         uses: actions/checkout@v2
       - name: Install pytorch
         run: |
           python3 -m pip cache dir
-          python3 -m pip install torch==2.1.0 torchvision==0.16.0
+          python3 -m pip install torch==2.3.0 torchvision==0.18.0
           # the install packeage from. https://github.com/Dao-AILab/flash-attention/releases
-          python3 -m pip install /root/packages/flash_attn-2.5.8+cu122torch2.1cxx11abiFALSE-cp310-cp310-linux_x86_64.whl
+          python3 -m pip install /root/packages/flash_attn-2.6.3+cu123torch2.3cxx11abiFALSE-cp310-cp310-linux_x86_64.whl
       - name: Build lmdeploy
         run: |
           python3 -m pip install cmake
           python3 -m pip install -r requirements/build.txt
+          wget https://download.open-mpi.org/release/open-mpi/v4.1/openmpi-4.1.5.tar.gz
+          tar xf openmpi-4.1.5.tar.gz && cd openmpi-4.1.5 && ./configure --prefix=/usr/local/openmpi
+          make -j$(nproc) && make install && cd .. && rm -rf openmpi-4.1.5*
+          export PATH=$PATH:/usr/local/openmpi/bin
+          export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/openmpi/lib
           mkdir build
           cd build
-          cp -r /nvme/qa_test_models/offline_pkg/_deps .
           cmake .. \
               -DCMAKE_BUILD_TYPE=RelWithDebInfo \
               -DCMAKE_EXPORT_COMPILE_COMMANDS=1 \
               -DCMAKE_INSTALL_PREFIX=/opt/tritonserver \
               -DBUILD_PY_FFI=ON \
               -DBUILD_MULTI_GPU=ON \
+              -DBUILD_CUTLASS_MOE=OFF \
+              -DBUILD_CUTLASS_MIXED_GEMM=OFF \
               -DCMAKE_CUDA_FLAGS="-lineinfo" \
-              -DUSE_NVTX=ON \
-              -DSM=80 \
-              -DCMAKE_CUDA_ARCHITECTURES=80 \
-              -DBUILD_TEST=OFF
+              -DUSE_NVTX=ON &&\
           make -j$(nproc) && make install
       - name: Install lmdeploy
         run: |
@@ -84,7 +88,8 @@ jobs:
           python3 -m pip list
           lmdeploy check_env
       - name: Test lmdeploy
-        run: CUDA_VISIBLE_DEVICES=5,6 pytest autotest -m pr_test -x --alluredir=allure-results --clean-alluredir
+        run: |
+          CUDA_VISIBLE_DEVICES=5,6 pytest autotest -m pr_test -x --alluredir=allure-results --clean-alluredir
       - name: Generate reports
         if: always()
         run: |