vllm
https://github.com/vllm-project/vllm
Python
A high-throughput and memory-efficient inference and serving engine for LLMs
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported43 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix] Reduce sparse-MLA + indexer workspace bounds on SM_120 (consumer Blackwell)
- [Frontend] Add optional llm_sign integration for OpenAI-compatible APIs
- [Bug]: Worker state update can raise KeyError on prev_req_id_to_index for a resumed AsyncLLM request
- Add opt-in draft vocab padding for speculative decoding
- with_cancellation can return None, causing FastAPI to send HTTP 200 with JSON null after http.disconnect
- [Bug]: `model.load_weights` silently corrupts MoE forward on second call
- [Bug]: MultiConnector _update_from_kv_xfer_finished error
- [Feature]: shuffle safetensor weight files
- Code quality scan: 233 findings (A-, 81/100)
- [Test] Add regression test for NVFP4 MoE dead-expert scale clamp (#42…
- Docs
- Python not yet supported