SGLang Llama Integration Tests #31
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: SGLang Llama Integration Tests | |
| on: | |
| workflow_dispatch: | |
| schedule: | |
| # Run periodically, every 4 hours. This is ran periodically with the | |
| # intent of catching regressions early, and allowing for those | |
| # regressions to be easily triaged to a small subset of commits. | |
| - cron: '0 */4 * * *' | |
| 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: | |
| sglang_bench_serve: | |
| name: "SGLang Integration Tests" | |
| strategy: | |
| matrix: | |
| version: [3.11] | |
| fail-fast: false | |
| runs-on: llama-mi300x-3 | |
| defaults: | |
| run: | |
| shell: bash | |
| env: | |
| PIP_CACHE_DIR: "${{ github.workspace }}/.pip-cache" | |
| steps: | |
| - name: Get Current Date | |
| id: date | |
| run: echo "::set-output name=date::$(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 -f https://iree.dev/pip-release-links.html --src deps \ | |
| -e "git+https://github.com/iree-org/iree-turbine.git#egg=iree-turbine" | |
| pip install --no-compile -r requirements.txt -e sharktank/ shortfin/ | |
| # Use newest possible releases to be able to track commits that may | |
| # cause errors. | |
| pip install -f https://iree.dev/pip-release-links.html --upgrade \ | |
| iree-base-compiler \ | |
| iree-base-runtime \ | |
| "numpy<2.0" | |
| - name: Install SGLang | |
| run: pip install "git+https://github.com/nod-ai/sglang.git#subdirectory=python" | |
| - name: Install sentence_transformers | |
| run: pip install sentence_transformers | |
| - name: Run Integration Tests | |
| run: pytest -v app_tests/integration_tests/llm/sglang --log-cli-level=INFO |