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 supported31 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Feature]: Simplify ROCm whl installation by removing libmpi_cxx dependency
- [Bugfix] Reject NVFP4 MoE checkpoints with missing per-expert scales
- [WideEP] Update DeepEP version in Dockerfile
- [ROCm] Fix sparse MLA invalid token kernel returning 0 instead of -1
- [Bugfix] Skip Ray actor kill after the driver has disconnected
- [Bugfix] Make block-fp8 fused MoE test tolerance noise-aware
- Add a debug tool to detect non-explicitly returned outputs under BCG
- [Model][Spec Decode] MiMo-V2.5-Pro-FP4 DFlash speculative decoding + AL fix
- [Bugfix] Resolve explicit store=null to the documented default in Responses API
- [Rust Frontend] Add mistral reasoning parser
- Docs
- Python not yet supported