QK^T rotates over five PSUM banks across Q groups when a group has <=2 key tiles, so it no longer waits on
the Vector row-max evict: attention device cycles -1.1% to -4.7% vs v1.3; 2048-token layout unchanged.
FP8 e4m3 double_row GELU MLP behind VIT_ENC_MLP_FP8=1 (off by default) with weight and per-layer activation
scaling. Verified on trn2.3xlarge: all 24 DINOv3 cases and V-JEPA2 pass.
27 days ago
v1: NKI kernels for RoPE ViT encoders (DINOv3, V-JEPA2) on Trainium2
