Skip to content

sdpa flash attention x86 optimization, llm models enable gqa, dispatch for avx2 bfloat2float - #6923

Open
nihui wants to merge 33 commits into
Tencent:masterfrom
nihui:sdpa-fa2
Open

sdpa flash attention x86 optimization, llm models enable gqa, dispatch for avx2 bfloat2float#6923
nihui wants to merge 33 commits into
Tencent:masterfrom
nihui:sdpa-fa2

Commits

Commits on Aug 18, 2026

Commits on Aug 20, 2026

  • committed

Commits on Aug 21, 2026

Commits on Aug 26, 2026

Commits on Aug 28, 2026

Commits on Aug 31, 2026

  • committed
  • committed
  • committed
  • committed
  • committed
  • nihuigithub-actions[bot]
    authored andcommitted
  • committed
  • committed
  • committed
  • committed
  • committed

Commits on Sep 1, 2026

  • committed
  • committed
  • committed