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
- [Attention] Move GDN common metadata compute out of per-group build
- [Metrics] Add operation label to Prometheus latency histograms
- [Quantization] Clarify MXFP4 MoE W13 layout requirement from backends
- [Bugfix] Handle persistent top-k candidate overflow
- [Feature] Add native forward-pass metrics emission
- Enhance engine snapshot management and API lifecycle
- [Quant] Add experimental online LUT-B quantization for MoE
- [Online quantization] Support activation quant key override
- [V1 Scheduler] Fix Priority Queue Preemption Re-admission (#41951)
- [Bugfix][MRv1] Decouple async Mamba align D2H counts from InputBatch row shifts (#51571)
- Docs
- Python not yet supported