Skip to content
inference.academy

glossary/tooling/flashinfer

FlashInfer

A kernel library for the operations serving engines share: attention over paged KV cache, in prefill and decode shapes, plus sampling, GEMM and MoE routines. It exists so that vLLM, SGLang and others do not each maintain their own attention kernels, and it is where techniques like block-sparse attention and cascade attention over shared prefixes are implemented once. Its kernels are JIT-compiled per shape and GPU.


one attention kernel

Shared by the major open engines, instead of one per engine.


Related