Skip to content

fix broken cuda and rocm images #552

fix broken cuda and rocm images

fix broken cuda and rocm images #552

name: CLI ROCm Pytorch Multi-GPU Tests
on:
workflow_dispatch:
push:
branches:
- main
paths:
- .github/workflows/test_cli_rocm_pytorch_multi_gpu.yaml
- "optimum_benchmark/**"
- "docker/**"
- "tests/**"
- "setup.py"
pull_request:
branches:
- main
paths:
- .github/workflows/test_cli_rocm_pytorch_multi_gpu.yaml
- "optimum_benchmark/**"
- "docker/**"
- "tests/**"
- "setup.py"
concurrency:
cancel-in-progress: true
group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
jobs:
run_cli_rocm_pytorch_multi_gpu_tests:
runs-on: [self-hosted, amd-gpu, multi-gpu]
container:
image: ghcr.io/huggingface/optimum-benchmark:latest-rocm
options: --ipc host
--shm-size "16gb"
--group-add video
--device /dev/kfd
--device /dev/dri
--env ROCR_VISIBLE_DEVICES
--env HIP_VISIBLE_DEVICES=0,1
--volume /mnt/cache/.cache/huggingface:/mnt/cache/
steps:
- name: Checkout code
uses: actions/checkout@v4
- name: Install dependencies
run: |
pip install -e .[testing,diffusers,timm,deepspeed,peft,autoawq,auto-gptq] "deepspeed<0.15"
- name: Run tests
run: |
pytest -x -s -k "cli and cuda and pytorch and (dp or ddp or device_map or deepspeed) and not bnb"