wehub-resource-sync
69 lines
2.0 KiB
YAML
69 lines
2.0 KiB
YAML
name: nv-flash-attn
|
|
|
|
on:
|
|
workflow_dispatch:
|
|
pull_request:
|
|
paths:
|
|
- 'deepspeed/sequence/**'
|
|
- 'tests/unit/sequence_parallelism/**'
|
|
- '.github/workflows/nv-flash-attn.yml'
|
|
schedule:
|
|
- cron: "0 0 * * *"
|
|
|
|
concurrency:
|
|
group: ${{ github.workflow }}-${{ github.ref }}
|
|
cancel-in-progress: true
|
|
|
|
jobs:
|
|
unit-tests:
|
|
name: nv-flash-attn / sequence parallelism tests
|
|
runs-on: [self-hosted, nvidia, a6000]
|
|
container:
|
|
image: nvcr.io/nvidia/pytorch:24.12-py3
|
|
ports:
|
|
- 80
|
|
options: --gpus all --shm-size "8G"
|
|
|
|
steps:
|
|
- uses: actions/checkout@v4
|
|
|
|
- name: Check container state
|
|
run: |
|
|
ldd --version
|
|
nvcc --version
|
|
nvidia-smi
|
|
python -c "import torch; print('torch:', torch.__version__, torch)"
|
|
python -c "import torch; print('CUDA available:', torch.cuda.is_available())"
|
|
|
|
|
|
|
|
- name: Install deepspeed
|
|
run: |
|
|
python -m pip install .[dev]
|
|
ds_report
|
|
|
|
# install transformers after deepspeed so that the right version of transformers is installed
|
|
- name: Install transformers
|
|
run: |
|
|
python -m pip install transformers==4.50.0
|
|
|
|
- name: Install FlashAttention
|
|
run: |
|
|
python -m pip install flash-attn
|
|
- name: Python environment
|
|
run: |
|
|
python -m pip list
|
|
- name: Unit tests
|
|
run: |
|
|
unset TORCH_CUDA_ARCH_LIST # only jit compile for current arch
|
|
cd tests
|
|
python -m pytest --color=yes --durations=0 --verbose -rF unit/sequence_parallelism/test_ulysses.py --torch_ver="2.6" --cuda_ver="12"
|
|
- name: Open GitHub issue if nightly CI fails
|
|
if: ${{ failure() && (github.event_name == 'schedule') }}
|
|
uses: JasonEtco/create-an-issue@v2
|
|
env:
|
|
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
|
with:
|
|
filename: .github/ISSUE_TEMPLATE/ci_failure_report.md
|
|
update_existing: true
|