CI - sharktank perplexity #112
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: CI - sharktank perplexity | |
| on: | |
| workflow_dispatch: | |
| schedule: | |
| # Weekdays nightly at 07:00 UTC = 23:00 PST / 00:00 PDT. | |
| - cron: "0 7 * * 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_perplexity_iree: | |
| if: ${{ github.repository_owner == 'nod-ai' || github.event_name != 'schedule' }} | |
| timeout-minutes: 1000 | |
| name: "Perplexity-IREE" | |
| strategy: | |
| matrix: | |
| version: [3.11] | |
| runs-on: [llama-mi300x-3] | |
| fail-fast: false | |
| runs-on: ${{matrix.runs-on}} | |
| defaults: | |
| run: | |
| shell: bash | |
| env: | |
| VENV_DIR: ${{ github.workspace }}/.venv | |
| steps: | |
| - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2 | |
| - name: "Setting up Python" | |
| id: setup_python | |
| uses: actions/setup-python@0b93645e9fea7318ecaed2b359559ac225c90a2b # v5.3.0 | |
| with: | |
| python-version: ${{matrix.version}} | |
| - name: Create Python venv | |
| run: python -m venv ${VENV_DIR} | |
| - name: Install sharktank deps | |
| run: | | |
| source ${VENV_DIR}/bin/activate | |
| 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-tubrine. | |
| 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" | |
| # Try with the latest IREE nightly releases, not what iree-turbine pins. | |
| # We could also pin to a known working or stable version. | |
| # This should eventually stabilize. Do the best we can for now. | |
| pip install -f https://iree.dev/pip-release-links.html --upgrade --pre \ | |
| iree-base-compiler \ | |
| iree-base-runtime | |
| pip freeze | |
| - name: Run perplexity test with IREE | |
| run: | | |
| source ${VENV_DIR}/bin/activate | |
| pytest -n 8 -v -s sharktank/tests/evaluate/perplexity_iree_test.py --run-nightly-llama-tests --bs=100 --iree-device='hip://7' --iree-hip-target=gfx942 --iree-hal-target-backends=rocm --llama3-8b-f16-model-path=/data/llama3.1/8b/llama8b_f16.irpa --llama3-8b-tokenizer-path=/data/llama3.1/8b/tokenizer_config.json --html=out/llm/llama/perplexity/iree_perplexity/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/perplexity/iree_perplexity | |
| destination_dir: ./llm/llama/perplexity/iree_perplexity | |
| keep_files: true | |
| test_perplexity_torch: | |
| if: ${{ github.repository_owner == 'nod-ai' || github.event_name != 'schedule' }} | |
| timeout-minutes: 1000 | |
| name: "Perplexity-Torch" | |
| strategy: | |
| matrix: | |
| version: [3.11] | |
| runs-on: [llama-mi300x-3] | |
| fail-fast: false | |
| runs-on: ${{matrix.runs-on}} | |
| defaults: | |
| run: | |
| shell: bash | |
| env: | |
| VENV_DIR: ${{ github.workspace }}/.venv | |
| steps: | |
| - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2 | |
| - name: "Setting up Python" | |
| id: setup_python | |
| uses: actions/setup-python@0b93645e9fea7318ecaed2b359559ac225c90a2b # v5.3.0 | |
| with: | |
| python-version: ${{matrix.version}} | |
| - name: Create Python venv | |
| run: python -m venv ${VENV_DIR} | |
| - name: Install sharktank deps | |
| run: | | |
| source ${VENV_DIR}/bin/activate | |
| 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-tubrine. | |
| 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" | |
| - name: Run perplexity test with Torch | |
| run: | | |
| source ${VENV_DIR}/bin/activate | |
| pytest -n 8 -v -s sharktank/tests/evaluate/perplexity_torch_test.py --longrun --llama3-8b-f16-model-path=/data/llama3.1/8b/llama8b_f16.irpa --llama3-8b-tokenizer-path=/data/llama3.1/8b/tokenizer_config.json --html=out/llm/llama/perplexity/torch_perplexity/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/perplexity/torch_perplexity | |
| destination_dir: ./llm/llama/perplexity/torch_perplexity | |
| keep_files: true |