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 supported59 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Perf][Kernel] Add opt-in BF16 gated projection fusion for SM89 prefills
- [Bugfix][Multimodal] Fix DP vision encoder hang: type an empty rank's output with the vision tower's output dtype
- [Bugfix][Frontend] Bound parallel sampling by server limits
- [CI] Recheck test coverage after shell script edits
- [WIP][FT] Pause healthy engines for recovery
- [Feature][PCP] Support DeepSeek V4 with FlashMLA on NVIDIA
- [Bugfix][Core] Bound local RPC ring-slot wait by deadline
- [Perf] Warm up JIT kernels that only long prefills, eager drafters and constrained decoding reach
- [Recipe] Kimi-K3, MiniMax-M3.1-Flash: add Rubin VR200 support
- [Perf][Sparse MLA][GLM-5.3] Index-group workspace savings and opt-in masked-MHA prefill on quantized KV
- Docs
- Python not yet supported