MLPerf inference DLRM-v2 #41
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # 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 DLRM-v2 | |
| on: | |
| schedule: | |
| - cron: "30 1 * * *" | |
| jobs: | |
| build_reference: | |
| if: github.repository_owner == 'gateoverflow' | |
| runs-on: [ self-hosted, GO-spr, linux, x64 ] | |
| strategy: | |
| fail-fast: false | |
| matrix: | |
| python-version: [ "3.12" ] | |
| device: [ "cpu" ] | |
| steps: | |
| - name: Test MLPerf Inference DLRM-v2 reference implementation | |
| run: | | |
| source gh_action/bin/deactivate || python3 -m venv gh_action | |
| source gh_action/bin/activate | |
| export CM_REPOS=$HOME/GH_CM | |
| python3 -m pip install cm4mlops | |
| cm pull repo | |
| cm run script --tags=run-mlperf,inference,_performance-only --adr.mlperf-implementation.tags=_branch.dev --adr.mlperf-implementation.version=custom --submitter="MLCommons" --model=dlrm-v2-99 --implementation=reference --backend=pytorch --category=datacenter --scenario=Offline --execution_mode=test --device=${{ matrix.device }} --docker --quiet --test_query_count=1 --target_qps=1 --docker_it=no --docker_cm_repo=gateoverflow@cm4mlops --adr.compiler.tags=gcc --hw_name=gh_action --docker_dt=yes --results_dir=$HOME/gh_action_results --clean | |
| build_intel: | |
| if: github.repository_owner == 'gateoverflow_off' | |
| runs-on: [ self-hosted, GO-spr, linux, x64 ] | |
| strategy: | |
| fail-fast: false | |
| matrix: | |
| python-version: [ "3.12" ] | |
| backend: [ "pytorch" ] | |
| device: [ "cpu" ] | |
| steps: | |
| - name: Test MLPerf Inference DLRM-v2 INTEL implementation | |
| run: | | |
| source gh_action/bin/deactivate || python3 -m venv gh_action | |
| source gh_action/bin/activate | |
| export CM_REPOS=$HOME/GH_CM | |
| python3 -m pip install cm4mlops | |
| cm pull repo | |
| cm run script --tags=run-mlperf,inference,_submission,_short --submitter="MLCommons" --model=dlrm-v2-99 --implementation=intel --batch_size=1 --backend=${{ matrix.backend }} --category=datacenter --scenario=Offline --execution_mode=test --device=${{ matrix.device }} --docker --quiet --test_query_count=1 --target_qps=1 --docker_it=no --docker_cm_repo=gateoverflow@cm4mlops --adr.compiler.tags=gcc --hw_name=gh_action --docker_dt=yes --results_dir=$HOME/gh_action_results --submission_dir=$HOME/gh_action_submissions --clean |