1.0 KiB
1.0 KiB
Contributing to vLLM-Omni
You may find information about contributing to vLLM-Omni on Contributing.
AI-assisted contributions must follow the AI Usage Policy, including disclosure, human review, and validation requirements.
Local pre-commit gates (SPDX, forbidden imports, torch.cuda, shellcheck,
mypy, test marks, TTS adapter ratchet, markdownlint, Buildkite schema, and
how to extend allowlists) are documented in the
Linting
section of that guide.
Before submitting a PR, run the precheck-pr skill with the code agent for a self-check against project conventions.
vLLM-Omni limits contributors without write access to 5 open PRs; see the Pull Request Limit section of the contributing guide.