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 supported62 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [XPU][Attention] Enable per-sequence causal masking with FA2
- [Bug]: Running GLM-5.3-Flash-NVFP4 on Hopper GPUs
- [Don't merge][Experiment] Move MediaIO decode to MM preprocessing
- [Bugfix] Apply structured output on /v1/completions when the prompt never opens reasoning
- Title
- [ROCm] Fuse DeepSeek V4.1 decode metadata and final norm
- [Bugfix][MRV1] Fix penalties with prompt embeddings
- [Security] Time out K2 Horizon and FunctionGemma tool-call regexes
- [Feature]: mega-MoE expert path for SM90 (H100/H20) DeepSeek-V4 / V4.1-Flash — Marlin weight-only is the only option today
- feat(chat): support OpenAI 'file' content parts by inlining documents as text
- Docs
- Python not yet supported