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 supported61 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Spec Decode] Fix Dspark adaptive verification cost model
- [Bug][PaliGemma] mm_prefix bidirectional ranges cover only the image tokens, not the instruction that follows
- [XPU] Route flash-attn imports through fa_utils in FlashAttn MLA sparse and dots3
- [Bugfix] Fix words lost at chunk cuts when transcribing long audio
- [MyPy] Complete kv-C and enforce KV connector tests
- [ROCm][Perf] Keep wvSplitK at YTILE 2 for N=5 on wave64 to avoid VGPR spills
- [LoRA][MoE] Expert LoRA for FlashInfer TRTLLM NVFP4 experts
- [wip][Spec Decode] Integrate EAGLE-4 through external plugin hooks
- [WIP][Spec Decode] Drafter early exit in a CUDA graph WHILE node
- [ROCm][MiMo] Add experimental FP8 blockscale mono MLP
- Docs
- Python not yet supported