24146733db
* use torch.cuda.current_device() instead of local_rank * ignore NVML errors for gpu stats * llama lora packing e2e tests
33 lines
699 B
YAML
33 lines
699 B
YAML
name: E2E
|
|
on:
|
|
workflow_dispatch:
|
|
|
|
jobs:
|
|
e2e-test:
|
|
runs-on: [self-hosted, gpu]
|
|
strategy:
|
|
fail-fast: false
|
|
matrix:
|
|
python_version: ["3.10"]
|
|
timeout-minutes: 10
|
|
|
|
steps:
|
|
- name: Check out repository code
|
|
uses: actions/checkout@v3
|
|
|
|
- name: Setup Python
|
|
uses: actions/setup-python@v4
|
|
with:
|
|
python-version: ${{ matrix.python_version }}
|
|
cache: 'pip' # caching pip dependencies
|
|
|
|
- name: Install dependencies
|
|
run: |
|
|
pip3 install -e .
|
|
pip3 install flash-attn
|
|
pip3 install -r requirements-tests.txt
|
|
|
|
- name: Run e2e tests
|
|
run: |
|
|
pytest tests/e2e/
|