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 supported48 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- feat: Add SM121/GB10 (DGX Spark) Blackwell-class GPU support
- [Feature]: Refactor the logic in tool parser manager and reasoning parser manager
- [Performance]: Update Cascade Attention Heuristics for FA3
- [Feature]: Composite model loading using `AutoWeightsLoader` for all models
- [V1][Experimental] Jump-forward decoding
- [V1][Scheduler] Use dict for running queue
- [WIP][RFC]: Use auto-functionalization V2 in PyTorch 2.7+
- [Feature]: `reasoning_tokens` in Chat Completion Response `usage`
- [Distributed] Add reduce_scatter to DeviceCommunicatorBase
- [Feature]: Implement Concurrent Partial Prefills In V1 Engine
- Docs
- Python not yet supported