Public
  1. Public

onnxruntime

Public

Commits

aciddelgadoGitHub
c181159783d
aciddelgado authored and GitHub committed 819b5a3eba8
Split KV on MHA and Attention ops (#18007)

### Description
Implement Split KV optimization for FlashAttention in MHA and Attention
operators.

### Motivation and Context
Can help further accelerate these ops.