FlashInfer

FlashInfer is our kernel library that implements high-performance operators for LLM Serving on GPUs.

• Project: FlashInfer
• Blog: FlashInfer Blog

People

Zihao Ye

Lequn Chen

Ruihang Lai

Yilong Zhao

Yifei Zuo

Yixin Dong

Size Zheng

Tianqi Chen

Assistant Professor - CMU

Luis Ceze

Professor