pub fn kquant_mmvq_experts_wn(
gpu: &dyn GpuBackend,
kernel: KernelHandle,
w_tables: DevicePtr,
y_q8: DevicePtr,
out_bf16: DevicePtr,
n: u32,
k: u32,
m: u32,
n_experts: u32,
y_stride_bytes: u32,
nwarps: u32,
stream: u64,
) -> Result<()>Expand description
kquant_mmvq_experts_w with nwarps rows a block (the _w2 / _w8
entries for 2 / 8; the plain _w entry is 4). Same bytes for any nwarps.