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
- [Transformers backend] Fuse MoE routers that score after the top-k
- [ROCm][Kimi-K3] Add moonmath kernels for gfx942 MXFP4 SiTU MoE and MLA decode, with decode context parallelism
- [Bugfix] Disable UVA in Confidential Computing mode to fix silent garbage output
- WIP: fix(decode bench): remember zero-token prefix fills
- [Kernel][MiniMax-M3] Add opt-in query-tiled sparse prefill
- [Scheduler] Balance async PP decode batches
- [GLM 5.3 Perf] Enable fused multi-step decode, 13.3% E2E throughput improvement for concurrency 1
- [Bugfix][Core] Retain fine-grained EAGLE replay checkpoints
- [RFC]: Layer-Wise Mixed-Precision KV Cache
- [Model Support] DeepSeek V4.1 Tracking Issue
- Docs
- Python not yet supported