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 supported26 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- fix(weight_loader): support scalar-to-array conversion for PerTensorScaleParameter
- [ROCm] Fix LDS bank conflicts in vecMatMul reduction_smem layout
- [Compilation] Drop closure indirection in `VllmPatternReplacement`
- fix: convert LogprobsLists to lists for cross node Ray transport (#38602)
- [ZenCPU] Route quantized linears through zentorch
- Add padding to support TP with Marlin linear kernel (NVFP4 on H100)
- [Multimodal] Simplify ViT CUDA graph interfaces
- Enable B12x backend for non-gated MoEs (like Nemotron)
- [Model][DeepSeekV4] Use FlashMLA KV-cache path for prefill
- [DP] External DP LB compatibility with all GPU visibility
- Docs
- Python not yet supported