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 supported19 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- add acceptance_threshold argument
- [DO NOT MERGE][Bugfix] Fix CPU memory leak in multimodal IPC sends
- [Bugfix] Fix MXFP4 weight_loader crash on per-expert 2-D weights
- [Misc] Redo quantized weights loading tracking
- Add encoder cache computation time tracking for replacement algorithm design
- [Bugfix][Hardware][AMD] Fix startup hang on ROCm gfx1151 in MinTokensLogitsProcessor
- [Bug]: FusedMoE.weight_loader MXFP4 branch crashes on standard HuggingFace MoE checkpoints (per-expert 2-D weights)
- Fix MoE models in EP mode on Ascend
- [Bugfix] Fix SymmMemCommunicator disabled on SM 10.3/12.0 GPUs
- [Test] Add some gsm8k configs for hybrid models.
- Docs
- Python not yet supported