FlashInfer is a library and kernel generator for Large Language Models that provides high-performance implementation of LLM GPU kernels such as FlashAttention, SparseAttention, PageAttention, Sampling ...
an open-source library for converting Chinese character variants to standard simplified or traditional characters. * About the project's name and logo: "CHAR" comes from "Chinese character variant" ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback