pub const W4A16_GEMV_OUTS_PER_BLOCK: u32 = 4;
Base w4a16_gemv: 4 outputs / 256-thread block. SSOT with kernels/**/w4a16_gemv.cu #define N_PER_BLOCK 4.
w4a16_gemv
kernels/**/w4a16_gemv.cu
#define N_PER_BLOCK 4