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 supported49 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Misc][Platform] Check aligned KV block sizes against every attention backend
- Revert "[DSpark] Support pipeline-parallel targets in aggregated serving (#56956)"
- [ROCm][MLA] Enable gfx942 DSpark+DCP verify on generic Triton
- [Bugfix][Core] Keep every multimodal feature in the partial-block KV event
- [Bugfix][Frontend][Rust Frontend] Update DeepSeek V4.1 Flash reasoning effort mappings
- [Structured Outputs] Parse Lark grammars natively in the xgrammar backend
- [Model] Add NemotronLabsDiffusion support with tri-mode inference
- [Feature] Add native ModelExpress weight transfer backend
- [Bugfix][V1][AsyncScheduler] Clamp delivered tokens to reserved output placeholders instead of killing EngineCore
- [Bugfix][MRV2] Treat padded prompt tails as spec-decode rows for hybrid models
- Docs
- Python not yet supported