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 supported31 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- Fix FA4 dynamic_causal for full attention layers
- Allow FlashInfer A2A backends for TRTLLM FP8 MoE Modular
- Rd fix spec tb combine overhead
- [KERNEL][ROCm]Native HIP MXFP4(Compressed+Quark) (dense + MoE) for RDNA3
- [XPU][Bugfix] Disable packed KV cache allocation on XPU for DeepSeek-V4
- [P/D][Bugfix][GLM5.2] Fix NIXL async KV load lookahead handling for MTP spec decode
- fix(security): Cap repetition_detection window to bound scheduler CPU…
- Add sycl kernel mhc path for dsv4
- [CI] Add registry layer cache to x86 CUDA release image builds
- [ROCm][DSV4] B-preshuffle the attention fp8 projections
- Docs
- Python not yet supported