Enabling CI for AMD with new runner..

This commit is contained in:
Nicolas Patry 2024-06-06 19:07:48 +02:00
parent ed1cfde0d8
commit 101ac9a760
1 changed files with 38 additions and 4 deletions

View File

@ -30,7 +30,7 @@ jobs:
cancel-in-progress: true
runs-on: [self-hosted, nvidia-gpu , multi-gpu, 4-a10, ci]
strategy:
matrix:
matrix:
include:
- name: "cuda"
label: ""
@ -123,19 +123,53 @@ jobs:
labels: ${{ steps.meta.outputs.labels || steps.meta-pr.outputs.labels }}
cache-from: type=registry,ref=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:cache${{ matrix.label }},mode=min
cache-to: type=registry,ref=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:cache${{ matrix.label }},mode=min
integration-tests-cuda:
concurrency:
group: ${{ github.workflow }}-${{ github.job }}-cuda-${{ github.head_ref || github.run_id }}
cancel-in-progress: true
runs-on: [self-hosted, nvidia-gpu , multi-gpu, 4-a10, ci]
needs: build-and-push-image
steps:
- name: Set up Python
if: matrix.name == 'cuda'
uses: actions/setup-python@v4
with:
python-version: 3.9
- name: Install
if: matrix.name == 'cuda'
run: |
make install-integration-tests
- name: Run tests
if: matrix.name == 'cuda'
run: |
export DOCKER_VOLUME=/mnt/cache
export DOCKER_IMAGE=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:sha-${{ env.GITHUB_SHA_SHORT }}
export HUGGING_FACE_HUB_TOKEN=${{ secrets.HUGGING_FACE_HUB_TOKEN }}
pytest -s -vv integration-tests
integration-tests-rocm:
concurrency:
group: ${{ github.workflow }}-${{ github.job }}-${{ github.head_ref || github.run_id }}
cancel-in-progress: true
runs-on: [amd-gpu-tgi, multi-gpu, mi250]
needs:
- build-and-push-image
steps:
- uses: actions/setup-python@v5
with:
python-version: '3.10'
- uses: actions/checkout@v4
- name: install deps
run: |
make install-integration-tests
- name: ROCM-SMI
run: |
rocm-smi
- name: ROCM-INFO
run: |
rocminfo | grep "Agent" -A 14
- name: Show ROCR environment
run: |
echo "ROCR: $ROCR_VISIBLE_DEVICES"
- name: Run tests
run: |
export DOCKER_IMAGE=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:sha-${{ env.GITHUB_SHA_SHORT }}
export HUGGING_FACE_HUB_TOKEN=${{ secrets.HUGGING_FACE_HUB_TOKEN }}
export DOCKER_DEVICES=/dev/kfd,/dev/dri
python -m pytest -s -vv integration-tests/models/test_flash_gpt2.py