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 supported51 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- feat(openai): add X-Trust human presence middleware
- [Bugfix][Spec Decode] Prevent missing KV scale parameter validation crash in Gemma4 MTP
- [Bug]: cuda_archs_loose_intersection drops plain "10.0" when TORCH_CUDA_ARCH_LIST also has "10.0a", producing sm_100a-only kernels that fail on B300 (CC 10.3)
- [Attention] SM120 NVFP4 KV cache on FlashInfer: HND layout + linear V scales
- [Distributed] Host-staged allreduce with NVFP4/FP8 codec (env-gated)
- [Spec Decode] SM120 DFlash/MTP: PP2 aux relay, NVFP4 draft startup, last-block drop
- [Bugfix][FlashInfer] Restrict W4A16 NVFP4 GEMM to SM100/103; fix CuTeDSL autotune op names
- [Bug]: JSON schema with multiple allOf branches is silently ignored by the xgrammar structured-output backend
- [Spec Decode][Perf] Add opt-in FP8 proposal head for Qwen4Exp MTP
- [Kernel] Avoid runtime alignment specialization in Triton MoE
- Docs
- Python not yet supported