mirror of
https://github.com/deepspeedai/DeepSpeed.git
synced 2025-10-20 15:33:51 +08:00
[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
This commit is contained in:
19
.github/workflows/xpu-max1100.yml
vendored
19
.github/workflows/xpu-max1100.yml
vendored
@ -36,7 +36,7 @@ jobs:
|
|||||||
unit-tests:
|
unit-tests:
|
||||||
runs-on: [self-hosted, intel, xpu]
|
runs-on: [self-hosted, intel, xpu]
|
||||||
container:
|
container:
|
||||||
image: intel/oneapi-basekit:2024.2.1-0-devel-ubuntu22.04
|
image: intel/oneapi-basekit:2025.0.1-0-devel-ubuntu24.04
|
||||||
ports:
|
ports:
|
||||||
- 80
|
- 80
|
||||||
options: --privileged -it --rm --device /dev/dri:/dev/dri -v /dev/dri/by-path:/dev/dri/by-path --ipc=host --cap-add=ALL
|
options: --privileged -it --rm --device /dev/dri:/dev/dri -v /dev/dri/by-path:/dev/dri/by-path --ipc=host --cap-add=ALL
|
||||||
@ -44,18 +44,23 @@ jobs:
|
|||||||
steps:
|
steps:
|
||||||
- uses: actions/checkout@v4
|
- uses: actions/checkout@v4
|
||||||
- name: Install prerequisite
|
- name: Install prerequisite
|
||||||
|
shell: bash
|
||||||
run: |
|
run: |
|
||||||
apt-get update
|
apt-get update
|
||||||
apt-get install clinfo libaio-dev python3-pip -y
|
apt-get install clinfo libaio-dev python3-pip python3.12-venv -y
|
||||||
pip install torch==2.3.1 -f https://pytorch-extension.intel.com/release-whl/stable/xpu/cn/torch/
|
python3 -m venv ~/ds_env
|
||||||
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/
|
source ~/ds_env/bin/activate
|
||||||
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 torch==2.5.1 -f https://pytorch-extension.intel.com/release-whl/stable/xpu/cn/torch/
|
||||||
pip install torchvision==0.18.1 -f https://pytorch-extension.intel.com/release-whl/stable/xpu/cn/torchvision/
|
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 py-cpuinfo numpy
|
||||||
pip install .[dev,autotuning]
|
pip install .[dev,autotuning]
|
||||||
|
|
||||||
- name: Check container state
|
- name: Check container state
|
||||||
|
shell: bash
|
||||||
run: |
|
run: |
|
||||||
|
source ~/ds_env/bin/activate
|
||||||
ldd --version
|
ldd --version
|
||||||
ds_report
|
ds_report
|
||||||
python3 -c "import torch; print('torch:', torch.__version__, torch)"
|
python3 -c "import torch; print('torch:', torch.__version__, torch)"
|
||||||
@ -64,7 +69,9 @@ jobs:
|
|||||||
pip list
|
pip list
|
||||||
|
|
||||||
- name: Unit tests
|
- name: Unit tests
|
||||||
|
shell: bash
|
||||||
run: |
|
run: |
|
||||||
|
source ~/ds_env/bin/activate
|
||||||
cd tests/unit
|
cd tests/unit
|
||||||
pytest --verbose accelerator/*
|
pytest --verbose accelerator/*
|
||||||
pytest --verbose autotuning/*
|
pytest --verbose autotuning/*
|
||||||
|
Reference in New Issue
Block a user