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 supported35 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Core][hybrid attention] group-aware recovery for KV load failures on hybrid models
- V1 multiprocess engine: sporadic 0.7-2s frozen engine step once per generate batch (absent with VLLM_ENABLE_V1_MULTIPROCESSING=0)
- [KV Connector][Mooncake] Skip lookup for locally reused prefix
- Update LayerNorm and dtype handling in gemma4_unified
- [Attention][TurboQuant] Optimize 4-bit GQA decode for group size 4
- [Bugfix] Fix Responses API crash on empty or refusal assistant content
- [Rust Frontend]: Add weight transfer lifecycle APIs
- fix: Domino inference patches for speculators-format checkpoints
- [Core] Add operator opt-out for the expandable_segments KV-connector rejection
- [DCP] Add FlashInfer fused A2A backend for decode context parallelism
- Docs
- Python not yet supported