pub fn ps_smem_bytes(mb: u32, sst: u32) -> u32Expand description
2026-09-25: Pure: the host side of the persistent entries’ launch contract
(w4a4_gemv_mx_ps.cuh): dynamic shared memory for mb column blocks with
sst k128 chunks staged per warp. 8 warps x sst x mb x (512 B of
fragments + 64 B of scales), plus the reduction buffer of RJ = 2 4 KiB
blocks that both entries instantiate.