Add new instances for merging multiple fwd conv groups into a single GEMM batch. Allow group merging for C > 1 when vector load/store size is 1 for the output tensor. (#3639)
Co-authored-by: Ville Pietilä <>
V
Ville Pietilä committed
7ac379428408337a231a86f8a8b7353b5b45aa2d
Parent: f5c2f09
Committed by GitHub <noreply@github.com>
on 1/25/2026, 12:42:23 PM