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 Mamba copy metadata high-bit pointers
- [MoE Refactor] Move capture state out of FusedMoE/MoERunner
- [Core] [Quantization] Pass `out_dtype` to linear methods
- [Bug]: Base model queries produce corrupt output when LoRA adapters are loaded on MoE models
- [Bug]: vLLM producing incorrect output for GLM-OCR
- [Bug]: NIXL connector silently disables HMA, halving KV cache capacity — flip default to HMA=on even with connectors
- [Bugfix] Reset offloader singleton in shutdown() to prevent GPU memory leak
- [Misc] Expose host RDMA devices to container in run_cluster.sh
- [Docs] Update server entrypoint examples
- [ROCm] Add RDNA support to wvSplitKrc skinny GEMM
- Docs
- Python not yet supported