paper7Updated Nov 21, 2026 · Português
← All papers

FlashInfer: Efficient and Customizable Attention Engine for LLM Inference Serving

Zihao Ye, Lequn Chen, Ruihang Lai, Wuwei Lin, Zhang, Yineng, Stephanie W. Wang, Tianqi Chen, Baris Kasikci and 3 more

Who it is from

  • Nvidiaaffiliation declared by the authors, according to OpenAlex

Other papers from the same organizations