[WIP] Add new GPU runner for E2E job, incorporate unit tests into existing runner #11
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
| # SPDX-License-Identifier: Apache-2.0 | |
| name: Test | |
| on: | |
| push: | |
| branches: | |
| - "main" | |
| - "release-**" | |
| paths: | |
| - '**.py' | |
| - 'pyproject.toml' | |
| - 'requirements*.txt' | |
| - '.github/workflows/test.yml' | |
| pull_request: | |
| branches: | |
| - "main" | |
| - "release-**" | |
| paths: | |
| - '**.py' | |
| - 'pyproject.toml' | |
| - 'requirements*.txt' | |
| - '.github/workflows/test.yml' | |
| concurrency: | |
| group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }} | |
| cancel-in-progress: true | |
| jobs: | |
| unit: | |
| runs-on: ubuntu-gpu | |
| steps: | |
| # No step-security/harden-runner since this is a self-hosted runner | |
| - name: Checkout instructlab/eval | |
| uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332 # v4.1.7 | |
| with: | |
| # https://github.com/actions/checkout/issues/249 | |
| fetch-depth: 0 | |
| # this is needed for branch tests | |
| - name: Checkout instructlab/taxonomy | |
| uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332 # v4.1.7 | |
| with: | |
| repository: "instructlab/taxonomy" | |
| path: "taxonomy" | |
| fetch-depth: 0 | |
| # this is needed for judge_answer tests | |
| - name: Checkout instructlab/instructlab | |
| uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332 # v4.1.7 | |
| with: | |
| repository: "instructlab/instructlab" | |
| path: "instructlab" | |
| fetch-depth: 0 | |
| - name: Install system packages | |
| run: | | |
| sudo apt-get install -y cuda-toolkit git cmake build-essential virtualenv | |
| nvidia-smi | |
| sudo ls -l /dev/nvidia* | |
| - name: Setup Python 3.11 | |
| uses: actions/setup-python@82c7e631bb3cdc910f68e0081d67478d79c6982d # v5.1.0 | |
| with: | |
| python-version: 3.11 | |
| cache: pip | |
| cache-dependency-path: | | |
| **/pyproject.toml | |
| **/requirements*.txt | |
| - name: Remove llama-cpp-python from cache | |
| run: | | |
| pip cache remove llama_cpp_python | |
| - name: Start inference server | |
| run: | | |
| export PATH="/home/runner/.local/bin:/usr/local/cuda/bin:$PATH" | |
| cd instructlab | |
| python3.11 -m venv cli_venv | |
| . cli_venv/bin/activate | |
| sed 's/\[.*\]//' requirements.txt > constraints.txt | |
| python3.11 -m pip cache remove llama_cpp_python | |
| CMAKE_ARGS="-DLLAMA_CUBLAS=on" python3 -m pip install --no-binary llama_cpp_python -c constraints.txt llama_cpp_python | |
| # needed for --4-bit-quant option to ilab train | |
| python3.11 -m pip install bitsandbytes | |
| # install instructlab | |
| python3.11 -m pip install . | |
| # start llama-cpp server | |
| ilab model download --repository instructlab/granite-7b-lab-GGUF --filename granite-7b-lab-Q4_K_M.gguf | |
| ilab model serve --model-path /home/runner/.local/share/instructlab/models/granite-7b-lab-Q4_K_M.gguf | |
| - name: Install dependencies | |
| run: | | |
| python3.11 -m venv venv | |
| . venv/bin/activate | |
| python3.11 -m pip install . | |
| python3.11 -m pip install pytest | |
| - name: Run unit tests | |
| run: | | |
| export INSTRUCTLAB_EVAL_FIRST_N_QUESTIONS=5 | |
| . venv/bin/activate | |
| python3.11 -m pytest | |
| - name: Remove llama-cpp-python from cache | |
| if: always() | |
| run: | | |
| pip cache remove llama_cpp_python |