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 supported29 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- fix: [Feature]: Support `Phi4Flash` model in V1
- [ROCm][CI] Gating more ROCm tests
- Improve Intel macOS CPU extension stability
- [ROCm][MLA] Fuse MLA q/kv RMSNorm + FP8 per-token quant in the FP8 attention path
- [Misc] Add KDA scaled-dot KKT test
- [Core][Eagle] Fix prefix cache efficiency in prefill phase
- [XPU] eplb
- [ROCm][Bugfix] Disable cudagraph for AITER MXFP4xMXFP4 MoE (graph-unsafe decode corruption)
- [Bugfix][Structured Output][Spec Decode] Advance grammar across reasoning boundary
- [Feature]: triton_scaled_mm uses an AMD-tuned fixed tile heuristic — leaves up to 1.82x on NVIDIA H800 (Hopper sm_90)
- Docs
- Python not yet supported