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 supported62 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: DFlash speculative decoding with gpt-oss target crashes with FA3 illegal memory access
- [ROCm][Attention] Honor VLLM_ROCM_USE_AITER=1 by ranking ROCM_AITER_FA above ROCM_ATTN
- [Bugfix][Kernel] MXFP4 cutlass MoE: fix experts quant out-of-bounds read for expert counts not divisible by 4 or 16
- [Bug]: DFlash drafter CUDA graph capture fails with FLEX_ATTENTION backend (seq_lens_cpu_upper_bound is None)
- [Bugfix][Responses] Default image detail in function tool outputs
- [Spec Decode] Support the Liquid LFM2.5-VL DSpark drafter
- [XPU][UT] Skip DeepSeek V4.1 initialization test on unsupported platforms
- [Bugfix][Reasoning] Stop kimi_k2 reasoning end check at the current turn
- [Bugfix][Tool Parser] Don't stream numbers in pythonic tool calls before they're complete
- [EPLB] Support heterogeneous DeepSeek V4/V4.1 DSpark draft experts
- Docs
- Python not yet supported