Skip to content

Llama2 gha selfhosted #407

Llama2 gha selfhosted

Llama2 gha selfhosted #407

# This workflow will install Python dependencies, run tests and lint with a variety of Python versions
# For more information see: https://help.github.com/actions/language-and-framework-guides/using-python-with-github-actions
name: MLPerf inference retinanet
on:
pull_request:
branches: [ "main", "dev", "mlperf-inference" ]
paths:
- '.github/workflows/test-mlperf-inference-retinanet.yml'
- '**'
- '!**.md'
jobs:
build:
runs-on: ubuntu-latest
strategy:
fail-fast: false
matrix:
python-version: [ "3.12" ]
backend: [ "onnxruntime", "pytorch" ]
implementation: [ "python", "cpp" ]
exclude:
- backend: pytorch
implementation: cpp
steps:
- uses: actions/checkout@v3
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v3
with:
python-version: ${{ matrix.python-version }}
- name: Install dependencies
run: |
python3 -m pip install cmind
cm pull repo --url=${{ github.event.pull_request.head.repo.html_url }} --checkout=${{ github.event.pull_request.head.ref }}
- name: Test MLPerf Inference Retinanet using ${{ matrix.backend }}
run: |
cm run script --tags=run,mlperf,inference,generate-run-cmds,_submission,_short --submitter="cTuning" --hw_name=default --model=retinanet --implementation=${{ matrix.implementation }} --backend=${{ matrix.backend }} --device=cpu --scenario=Offline --test_query_count=5 --adr.compiler.tags=gcc --quiet -v --target_qps=1