Skip to content

Update llm perf

Update llm perf #361

name: CLI CUDA OnnxRuntime Tests
on:
workflow_dispatch:
push:
branches: [main]
pull_request:
types: [opened, reopened, synchronize]
concurrency:
group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
cancel-in-progress: true
jobs:
run_cli_cuda_onnxruntime_tests:
runs-on: [single-gpu, nvidia-gpu, a10, ci]
steps:
- name: Checkout
uses: actions/checkout@v3
- name: Pull image
run: docker pull pytorch/pytorch:2.2.2-cuda11.8-cudnn8-runtime
- name: Run tests
uses: addnab/docker-run-action@v3
with:
image: pytorch/pytorch:2.2.2-cuda11.8-cudnn8-runtime
options: |
--rm
--gpus all
--shm-size 64G
--env MKL_THREADING_LAYER=GNU
--volume ${{ github.workspace }}:/workspace
--workdir /workspace
run: |
pip install -e .[testing,onnxruntime-gpu,diffusers,timm]
pytest -x -s -k "cli and cuda and onnxruntime"