[XPU] max1100 workflow update for docker and softwares (#7003)

1. update intel oneAPI basekit to 2025.0 2. update torch/ipex/oneccl to 2.5 Signed-off-by: Logan Adams <[email protected]>
deepspeedai · Feb 7, 2025 · 4557ab8 · 4557ab8
1 parent 81032c2
commit 4557ab8
Showing 1 changed file with 13 additions and 6 deletions.
diff --git a/.github/workflows/xpu-max1100.yml b/.github/workflows/xpu-max1100.yml
@@ -36,26 +36,31 @@ jobs:
   unit-tests:
     runs-on: [self-hosted, intel, xpu]
     container:
-      image: intel/oneapi-basekit:2024.2.1-0-devel-ubuntu22.04
+      image: intel/oneapi-basekit:2025.0.1-0-devel-ubuntu24.04
       ports:
         - 80
       options: --privileged -it --rm --device /dev/dri:/dev/dri -v /dev/dri/by-path:/dev/dri/by-path --ipc=host --cap-add=ALL
 
     steps:
     - uses: actions/checkout@v4
     - name: Install prerequisite
+      shell: bash
       run: |
         apt-get update
-        apt-get install clinfo libaio-dev python3-pip -y
-        pip install torch==2.3.1 -f https://pytorch-extension.intel.com/release-whl/stable/xpu/cn/torch/
-        pip install intel-extension-for-pytorch==2.3.110+xpu -f https://pytorch-extension.intel.com/release-whl/stable/xpu/cn/intel-extension-for-pytorch/
-        pip install oneccl_bind_pt==2.3.100+xpu -f https://pytorch-extension.intel.com/release-whl/stable/xpu/cn/oneccl-bind-pt/
-        pip install torchvision==0.18.1 -f https://pytorch-extension.intel.com/release-whl/stable/xpu/cn/torchvision/
+        apt-get install clinfo libaio-dev python3-pip python3.12-venv -y
+        python3 -m venv ~/ds_env
+        source ~/ds_env/bin/activate
+        pip install torch==2.5.1 -f https://pytorch-extension.intel.com/release-whl/stable/xpu/cn/torch/
+        pip install intel-extension-for-pytorch==2.5.10+xpu -f https://pytorch-extension.intel.com/release-whl/stable/xpu/cn/intel-extension-for-pytorch/
+        pip install oneccl_bind_pt==2.5.0+xpu -f https://pytorch-extension.intel.com/release-whl/stable/xpu/cn/oneccl-bind-pt/
+        pip install torchvision==0.20.1 -f https://pytorch-extension.intel.com/release-whl/stable/xpu/cn/torchvision/
         pip install py-cpuinfo numpy
         pip install .[dev,autotuning]
 
     - name: Check container state
+      shell: bash
       run: |
+        source ~/ds_env/bin/activate
         ldd --version
         ds_report
         python3 -c "import torch; print('torch:', torch.__version__, torch)"
@@ -64,7 +69,9 @@ jobs:
         pip list
 
     - name: Unit tests
+      shell: bash
       run: |
+        source ~/ds_env/bin/activate
         cd tests/unit
         pytest --verbose accelerator/*
         pytest --verbose autotuning/*