Skip to content

Cortex-M: fold constant attention-score scale into the softmax-input quantize#21027

Open
rascani wants to merge 1 commit into
pytorch:mainfrom
rascani:cortexm-scale-fold
Open

Cortex-M: fold constant attention-score scale into the softmax-input quantize#21027
rascani wants to merge 1 commit into
pytorch:mainfrom
rascani:cortexm-scale-fold

Commits

Commits on Jul 16, 2026