[RL] support only do cpu backup on draft model #995
Workflow file for this run
This file contains hidden or 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
| name: Quantization Test | |
| on: | |
| push: | |
| branches: [ main ] | |
| paths: | |
| - "python/**" | |
| - "!python/sglang/multimodal_gen/**" | |
| - "scripts/ci/**" | |
| - "test/**" | |
| - ".github/workflows/quantization-test.yml" | |
| pull_request: | |
| branches: [ main ] | |
| paths: | |
| - "python/**" | |
| - "!python/sglang/multimodal_gen/**" | |
| - "scripts/ci/**" | |
| - "test/**" | |
| - ".github/workflows/quantization-test.yml" | |
| types: [synchronize, labeled] | |
| workflow_dispatch: | |
| concurrency: | |
| group: quantization-test-${{ github.ref }} | |
| cancel-in-progress: true | |
| jobs: | |
| quantization-test: | |
| if: github.event_name != 'pull_request' || contains(github.event.pull_request.labels.*.name, 'run-ci') | |
| runs-on: 1-gpu-runner | |
| steps: | |
| - name: Checkout code | |
| uses: actions/checkout@v4 | |
| - name: Install dependencies | |
| run: | | |
| bash scripts/ci/ci_install_dependency.sh | |
| pip install "bitsandbytes>=0.44.0" | |
| - name: Run Quantization tests | |
| timeout-minutes: 30 | |
| run: | | |
| cd test/srt | |
| python3 run_suite.py --suite quantization_test |