w8a16_gemm

Function w8a16_gemm 

Source
pub fn w8a16_gemm(
    gpu: &dyn GpuBackend,
    kernel: KernelHandle,
    input: DevicePtr,
    weight: DevicePtr,
    block_scale: DevicePtr,
    output: DevicePtr,
    m: u32,
    n: u32,
    k: u32,
    stream: u64,
) -> Result<()>
Expand description

W8A16 GEMM (M>1): C[M,N] = A[M,K] @ dequant(B[N,K]) for prefill.

Uses 256-entry E4M3 LUT + BF16 2D block scales. Grid: (ceil(N/64), ceil(M/64), 1) Block: (128, 1, 1)