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 structured output support for beam search in online serving
- full cudagraph for flex-attn
- Fused BMM+FP8 quant Triton kernel for MLA _v_up_proj (forward_mqa path)
- [Attention] Add FlashInfer FA2 MLA attention backend for SM120
- [Bug]: Unsupported Activation Function for Step-3.5-Flash
- Replace shape_invariants with simpler apprach in dynamic_arg_dims utilizing shape_id property.
- [Bugfix] Fix Qwen3.5 Marlin TP failure for GDN in_proj_ba
- Fix multi-node WorkerProc init ordering and compilation_time None
- [Bug]: The checkpoint you are trying to load has model type `qwen3_5` but Transformers does not recognize this architecture
- [Performance] Add CUDA graph optimization for classify pooler
- Docs
- Python not yet supported