Skip to content

contributors.md

Latest commit

 

History

History
29 lines (24 loc) · 1.49 KB

contributors.md

File metadata and controls

29 lines (24 loc) · 1.49 KB
Raw

Release validation

  1. Open a release PR and wait for CI to pass.

  2. On each Linux x86-64 GPU machine, check out the PR head and build its native tests locally. Install test dependencies, model data, GPU drivers, and runtime libraries, including a GPU-compatible PyTorch. Authenticate with gh auth login using an account permitted to download artifacts and write commit statuses.

  3. Run the native and Python tests, including GPU tests:

    bash tools/release-check.sh cuda

    Replace cuda with rocm on the AMD machine.

The script finds the current branch's PR in the GitHub repository named by origin. It checks that tracked files are clean and HEAD matches the PR, then publishes release/cuda or release/rocm as pending, then success or failure. It downloads the CUDA or ROCm wheel from the latest push CI run for that exact commit. Wait for the wheel artifact to be uploaded before running validation. The wheel is installed into a temporary environment that reuses your Python dependencies; the environment is removed afterwards. Your installed CTranslate2 is left untouched. Native tests use your local build, since CI does not upload it. The script requires a visible GPU and both test commands to pass. Detailed output stays in the terminal.

Configure both statuses as required checks for release PRs. Re-run validation for every new commit. Publish the validated artifacts after CI and both GPU checks pass; validate again if the final release changes the tested code.