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
- [Model] Allow Gemma4 to use FlashInfer when FA4 is unavailable
- [Bug]: REGRESSION : FP8 KV cache FlashInfer no longer available as attention backend on SM75 (Turing) in v0.24.0
- [Attention][TurboQuant] Preserve configured FlashAttention version
- [Bug]: Combination of sleep mode and speculative decoding cause crash (ROCm / MI250)
- fix(quant): forward MiniMax M3 SwiGLU parameters to FusedMoEQuantConfig in int8 paths
- [Bug]: Gemma4 (probably other models with missing v_proj) breaks with mixed quantization
- [Bugfix] Allow untyped tool schemas to coerce JSON values
- [Feature]: Support NVIDIA Nemotron 3.5 ASR Streaming (nemotron-3.5-asr-streaming-0.6b)
- [Perf] Maintain persistent penalty statistics instead of per-step CPU rebuild in V1 sampler
- [ROCm][Perf] Enable fused indexer-Q RoPE+quant kernel for DeepSeek/GLM sparse attention
- Docs
- Python not yet supported