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
- [Model] Mistral Llama 4 scaling: compute once per forward, reuse across layers
- [ROCm][Perf] Use the fused clamped SwiGLU kernel on ROCm
- [Bugfix] Make Triton MoE reduction pad-aware under EP
- [Bugfix] Name the real cause when a TurboQuant layer resolves to "auto"
- [ROCm][AITER] Add support for new per-stream workspace requirement by AITER v0.1.20
- [Core] Make optional module discovery side-effect-free
- [SpecDecode] Preserve reject-only residual verifier padding
- [Feature]: KV cache group splitting assumes n:1 pattern between attention types
- [Bugfix] Remove Coincidentally-Correct Tests
- [MoE][DeepEPV2] Add PaddedStandard activation format
- Docs
- Python not yet supported