transpose_nvfp4_packed_kton

spark_runtime::cutlass

Function transpose_nvfp4_packed_kton 

Source 
pub fn transpose_nvfp4_packed_kton(
    src_packed_t: u64,
    dst_packed: u64,
    n: u32,
    k: u32,
    stream: u64,
) -> Result<()>
Expand description

Transpose an Atlas-packed NVFP4 weight from the checkpoint/hand-kernel [K/2, N] layout into CUTLASS’s [N, K/2] layout (the byte order the native NVFP4 GEMM consumes for the ColumnMajor B operand). Pure byte transpose; nibble pairing within each byte is preserved. dst_packed must have N * K/2 bytes.