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 supported52 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug][Spec Decode] MRV2 AutoRegressiveSpeculator ignores dynamic K from scheduler — DSD non-functional on MRV2
- [Bugfix][ROCm] Disable skinny GEMM on gfx1151
- [ROCm][AITER] Port FlyDSL int4 MoE integration to AITER fused_moe API
- [Model Loader] Add FastSafetensors sharded-state loader
- [Bug]: Qwen3.5 122b a10 model RuntimeError: Triton Error [CUDA]: an illegal memory access was encountered
- [RFC] Multimodal RL inputs for /inference/v1/generate
- fix(anthropic): preserve requested model alias in messages response
- [Bug]: Explicit VLLM_CUTLASS NVFP4 MoE selection silently produces empty completions on SM_120
- [Bugfix][Model] Fail fast on Inkling's unsupported GPU architectures
- [ROCm][Perf] Skip cleaning sparse prefill MQA logits
- Docs
- Python not yet supported