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 supported61 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [KV Offload] Bound staged loads by primary tier capacity
- [KV Offload] Mirror CPU offload region slots across nodes
- [Bugfix][Responses] Reject negative starting_after in event replay
- [Bugfix][Multimodal] Enforce decode-byte budget for numpy image_embeds
- [Bugfix][Frontend] Allow opt-in prompt id reuse without a KV connector
- [Core][KVConnector] Connector "ready" state for asynchronous connector startup
- [Perf][GDN] Run short prefills through the recurrent kernel with the decodes
- [Perf][Model] Qwen4Exp QSA: SM80 launch config for indexer prefill scoring
- [MRV2][BugFix] Don't expose P/D step output before drafter KV writes complete
- [Bug]: Qwen3-ASR realtime flush emits the tail as a fresh ChatML prompt with no left audio
- Docs
- Python not yet supported