Skip to content

flash_attention: prologue fusion, mma tensor cores, fp8 KV cache, flex attention + block sparsity - #7

Merged
morousg merged 11 commits into
Libraries-Openly-Fused:mainfrom
johnnynunez:main
Jun 24, 2026
Merged

flash_attention: prologue fusion, mma tensor cores, fp8 KV cache, flex attention + block sparsity#7
morousg merged 11 commits into
Libraries-Openly-Fused:mainfrom
johnnynunez:main

Commits

  1. Commits on Jun 11, 2026

  2. Commits on Jun 24, 2026