Function gemv_mma_launch 

pub fn gemv_mma_launch(
    m: usize,
    n: usize,
    k: usize,
    sms: usize,
) -> (usize, usize, usize, usize)

lk_gemv_mma’s launch over m rows (at most GEMV_MMA_ROWS) of a projection of n outputs and k on a chip of sms multiprocessors, (mt, nt, mw, nw): the widest tile its rows fill (gemv_mma_shape), except that a narrow projection of long rows over four m-tiles — its blocks of 128 outputs leaving more than half the chip idle, each running long (k at least 2048) — takes blocks of 64 outputs, twice as many. On the 3060 at 64 rows: Gemma-3-1B’s down projection (6912 by 1152) 94 µs to 54 (62 as the 32-row tile in two slabs of grid layers), Qwen3.5-0.8B’s (3584 by 1024) 54 to 31 (35) and its output projection (2048 by 1024) 33 to 20 (22); wider or shorter projections are faster in blocks of 128.