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 supported59 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix][Model] Inkling: skip EP-alignment padding experts when loading expert weights
- test_process_checkpoint: no coverage path for hybrid GDN models
- [Test] Support hybrid GDN models in test_process_checkpoint
- [Bug]: vllm-rs chat render and native render select opposite thinking modes when a thinking toggle is combined with a reasoning-effort control
- [Bug]: DeepSeek render parity — native appends EOS for continue_final_message, vllm-rs does not
- [Bug]: DeepSeek tool-schema JSON omits "description": null in vllm-rs (native includes it)
- [Feature] Add MXFP8 expert online quantization to DeepGEMM MegaMoE
- [RFC]: DBO for the MTP/EAGLE drafter forward in Model Runner V2
- [RFC]: DBO for the decoder of multimodal MoE models in Model Runner V2
- [RFC]: DBO with the allgather_reducescatter all2all backend on CUDA
- Docs
- Python not yet supported