Function w4a16_tc_rows 

pub fn w4a16_tc_rows(
    gpu: &dyn GpuBackend,
    input: DevicePtr,
    weight: &QuantizedWeight,
    output: DevicePtr,
    m: u32,
    n: u32,
    k: u32,
    lda: u32,
    ldc: u32,
    stream: u64,
) -> Result<()>

2026-10-02: output [m, ldc] = input [m, lda] x W^T for the row-major NVFP4 weight [n, k] (packed E2M1, E4M3 scales of 16, weight_scale_2). Refuses a shape w4a16_tc_rows_shape_ok refuses.