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 supported31 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Frontend] Replace xgrammar's built-in structural tag with vLLM's implementation
- [Feat] Support FlashQLA backend for qwen3.5
- [XPU][MiniMax-M3] Add XPU support for MSA sparse-attention path + tune gemma_rmsnorm for BMG
- [Bugfix] Fix CPU split-KV scratchpad sizing
- [Performance]: TTFT of graph mode is about 25% worse than that of eager mode.
- [Misc] Support exporting torch profiler table as CSV or JSON
- [ROCm][DSv4] Add AITER MXFP4-MXFP8 W4A8 MoE backend
- [Misc] Add pure decode throughput to `vllm bench serve` results
- [Kernel] Opt-in fused shared-expert gate + GDN in-proj fusion + prefill scan-output copy elision for Qwen3.5-122B-A10B-NVFP4 (Blackwell SM103)
- [MoE] Plumb gemm1_alpha/beta/clamp_limit into TRT-LLM FP8 MoE
- Docs
- Python not yet supported