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][V1] Use the Mamba cache group's block size for align-mode chunk splitting
- [Bug]: DFlash2 + YaRN identical 1.04M prompt gets zero prefix-cache reuse while target-only reuses ~1.039M tokens
- [Model] Support Ling 3.0 D-Spark serving
- fix: enable ROCM_AITER_FA with Eagle3 spec decode
- [Bugfix][EPD] Preserve upstream status and error details in proxy responses
- [Bug]: an installed-but-unusable optional dependency (boto3) aborts model architecture resolution for every model
- [ROCm][Perf] Enable AITER fuse_qk_norm_rope_kvcache for Gemma4 (head_dim 512 + V-norm)
- [Bugfix] Await the accepted-token copy before moving batch rows
- [Bugfix] Keep think tokens that appear after reasoning ends
- [Attention] Warn once when speculative decoding forces the Triton unified-attention 2D decode path
- Docs
- Python not yet supported