pub fn fp4_act_scratch_bytes(m: u32, k: u32) -> usizeExpand description
block_fp4_mmq activation scratch bytes for [m, k]. +1MB slack: the kernel’s smem copy loop rounds the last y-slice read up to warp granularity (same convention as q8_1_scratch_bytes). Always ≤ q8_1_scratch_bytes(m, k) → fits the shared ffn_act_q8.