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 supported37 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Regression]: MiniMax-M3 leading `</mm:think>` bypasses the reasoning parser on v0.26.0 and current main
- [Bugfix][NIXL] Handle decode allocating more blocks than prefiller in prefix caching
- [Bugfix] Validate tensor dtypes in the moe_wna16 GEMM op wrappers
- [ROCm][Bugfix] Keep the MLA query in bf16 for AITER Gluon fp8 KV decode
- [Reload] Probe dummy-load manifests for layerwise reload
- [Bug]: AxionML/Gemma-4-12B-NVFP4 fails with shape mismatch in flashinfer_scaled_fp4_mm on RTX 5060 Ti (sm_120)
- [DCP] Default query replication for GLM sparse attention
- [Bug]: Blocking issue of `MessageQueue.dequeue` in multi-threaded environments
- [Performance][MooncakeStoreConnector] Overlapping async cold-prefix loads cause duplicate Gets into distinct GPU blocks
- [Bugfix] Fix six quantization exception messages split across positional args
- Docs
- Python not yet supported