Use iree_device to run tests on different hip devices to avoid conflict/queue times #52
Workflow file for this run
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
| # Copyright 2024 Advanced Micro Devices, Inc. | |
| # | |
| # Licensed under the Apache License v2.0 with LLVM Exceptions. | |
| # See https://llvm.org/LICENSE.txt for license information. | |
| # SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception | |
| name: Llama Benchmarking Tests | |
| on: | |
| workflow_dispatch: | |
| pull_request: | |
| schedule: | |
| # Weekdays at 4:00 AM UTC = 9:00 PM PST. | |
| - cron: "0 4 * * 1-5" | |
| concurrency: | |
| # A PR number if a pull request and otherwise the commit hash. This cancels | |
| # queued and in-progress runs for the same PR (presubmit) or commit | |
| # (postsubmit). The workflow name is prepended to avoid conflicts between | |
| # different workflows. | |
| group: ${{ github.workflow }}-${{ github.event.number || github.sha }} | |
| cancel-in-progress: true | |
| jobs: | |
| test_llama_large: | |
| if: ${{ github.repository_owner == 'nod-ai' || github.event_name != 'schedule' }} | |
| name: "Llama Benchmarking Tests" | |
| strategy: | |
| matrix: | |
| version: [3.11] | |
| fail-fast: false | |
| runs-on: llama-mi300x-1 | |
| defaults: | |
| run: | |
| shell: bash | |
| env: | |
| PIP_CACHE_DIR: "${{ github.workspace }}/.pip-cache" | |
| VENV_DIR: ${{ github.workspace }}/.venv | |
| steps: | |
| - name: Get Current Date | |
| id: date | |
| run: echo "::set-output name=date::$(date +'%Y-%m-%d')" | |
| - name: "Setting up Python" | |
| id: setup_python | |
| uses: actions/setup-python@0b93645e9fea7318ecaed2b359559ac225c90a2b # v5.3.0 | |
| with: | |
| python-version: ${{matrix.version}} | |
| - name: "Checkout Code" | |
| uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2 | |
| - name: Cache Pip Packages | |
| uses: actions/cache@6849a6489940f00c2f30c0fb92c6274307ccb58a # v4.1.2 | |
| id: cache-pip | |
| with: | |
| path: ${{ env.PIP_CACHE_DIR }} | |
| key: pip-${{ steps.setup_python.outputs.python-version }}-${{ hashFiles('*requirements.txt') }} | |
| - name: Install pip deps | |
| run: | | |
| python -m pip install --no-compile --upgrade pip | |
| # Note: We install in three steps in order to satisfy requirements | |
| # from non default locations first. Installing the PyTorch CPU | |
| # wheels saves multiple minutes and a lot of bandwidth on runner setup. | |
| pip install --no-compile -r pytorch-cpu-requirements.txt | |
| pip install --no-compile -r requirements.txt -r sharktank/requirements-tests.txt -e sharktank/ | |
| # Install latest iree-turbine. | |
| pip install --no-compile -f https://iree.dev/pip-release-links.html --src deps \ | |
| -e "git+https://github.com/iree-org/iree-turbine.git#egg=iree-turbine" | |
| # Test with nightly releases, not what iree-turbine uses. | |
| pip install -f https://iree.dev/pip-release-links.html --upgrade --pre \ | |
| iree-base-compiler \ | |
| iree-base-runtime | |
| - name: Run llama tests | |
| run: pytest sharktank/tests/models/llama/benchmark_amdgpu_test.py -v -s --run-nightly-llama-tests --iree-hip-target=gfx942 --iree-device=7 --html=out/llm/llama/benchmark/index.html | |
| - name: Deploy to GitHub Pages | |
| uses: peaceiris/actions-gh-pages@4f9cc6602d3f66b9c108549d475ec49e8ef4d45e # v4.0.0 | |
| with: | |
| github_token: ${{ secrets.SHARK_PLATFORM_GH_TOKEN }} | |
| publish_dir: ./out/llm/llama/benchmark | |
| destination_dir: ./llm/llama/benchmark | |
| keep_files: true | |
| - name: Upload llama executable files | |
| uses: actions/upload-artifact@b4b15b8c7c6ac21ea08fcf65892d2ee8f75cf882 # v4.4.3 | |
| with: | |
| name: llama-files | |
| path: ${{ github.workspace }}/${{ steps.date.outputs.date }} |