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
- [Prototype][MRV2] Grammar spec dec (jump decoding) for structured outputs
- [RFC]: Forward ReqContext from CPUOffloadingManager to CachePolicy for session-aware KV eviction
- [Bug]: Scheduler deadlocks without KV-cache connector
- Fix/qwen3 reasoning to content in short resp
- Performance tips for AMD MI210?
- [Bugfix][ToolParser] Make Hermes streaming tool call boundaries JSON string aware
- [Feature]: Simplify ROCm whl installation by removing libmpi_cxx dependency
- [Bugfix] Reject NVFP4 MoE checkpoints with missing per-expert scales
- [ROCm] Fix sparse MLA invalid token kernel returning 0 instead of -1
- [Bugfix] Skip Ray actor kill after the driver has disconnected
- Docs
- Python not yet supported