W4A16_GEMV_SW_OUTS_PER_BLOCK

metrale_model_layers::layers::ops

Constant W4A16_GEMV_SW_OUTS_PER_BLOCK 

Source 
pub const W4A16_GEMV_SW_OUTS_PER_BLOCK: u32 = 8;
Expand description

2026-09-25: Outputs per 256-thread block of the single-warp kernels (w4a16_gemv_sw and the _sw kernels in w4a16_gemv_fused.cu); equals #define N_PER_BLOCK_SW.