Constant W4A16_VIA_FP8_MIN_M 

pub const W4A16_VIA_FP8_MIN_M: u32 = 1024;

2026-09-28: Rows at or above which w4a16_t_via_fp8_ldmab beats w4a16_gemm_t_m128 on the dense 27B attention projections (dgx2: x1.23-1.35 at 1024 rows, x0.69 at 300, x2.15 at 8192): below it the per-call weight dequant dominates.