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)