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 supported36 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix] Initialize DeepGemmQuantScaleFMT oracle lazily; bound QuantFP8 UE8M0 packed path to group_size 128
- [Core][KV Events] Echo session_id on GPU BlockStored events
- [Core][V1] Add bounded session-affinity scheduler
- [Bug]: LoRA set_lora on merged QKV/gate_up raises IndexError when lora_a is a single tensor
- Add SM90 FA4 Dense and MLA
- [Bug]: Kimi K3 usage.prompt_tokens over-counts trailing channel-open stub (+3)
- [Bugfix] Stop fusing scale_ue8m0=True group quant into ue8m0-unaware fused kernels
- [Perf] Use the fused rotary_embedding kernel in DeepseekScalingRotaryEmbedding without FlashInfer
- [Bugfix] Use the V2 model runner for Gemma 4 MoE so MTP drafting works
- [Bugfix] Save logical sharded state before postprocessing
- Docs
- Python not yet supported