Files
nvfp4-megamoe-kernel/dsv4/kernels/attention
biondizzle 016edbcc97 D5c: add row_sum output for proper external normalization
The kernel's O_unnorm is max-shifted (divided by 2^row_max), so
O_norm != O_unnorm * exp(-LSE). Instead, O_norm = O_unnorm / row_sum.
Added mRowSums output tensor to enable correct normalization.
2026-05-26 15:07:22 +00:00
..
2026-05-23 20:08:31 +00:00