pub const NVFP4_LEAN_REPACK_SMEM_PER_K: u32 = 9;
2026-10-04: Shared bytes nvfp4_tc_lean_repack stages per unit of K: a 16-row tile’s packed (16 * K / 2) and scale (16 * K / 16) bytes.
nvfp4_tc_lean_repack