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 supported51 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix] Stop Kimi K3 end-of-turn marker leaking into streamed content
- [Bugfix][ROCm] Route non-divisor small-head MLA decode to Gluon on gfx950
- Added the fix for deepseek on xpu
- [Engine Core] Gather engine notifications from workers to frontends
- [Bug]: Hybrid sparse attention + Eagle results in full cache miss for certain prompt lengths
- Bound DeepSeek OCR no-repeat scanning
- Confine connector cache files to shared storage
- [Bug]: online FP8 (--quantization fp8) produces corrupted, non-EOS-terminating output on Qwen2.5-1.5B-Instruct
- Add distributed LegoMem KV offload benchmark
- [Bugfix][DSv4] Skip zero-query-len prefill chunks in FlashMLA sparse prefill (complements #49059)
- Docs
- Python not yet supported