pub fn dense_gemm(
gpu: &dyn GpuBackend,
kernel: KernelHandle,
input: DevicePtr,
weight: &DenseWeight,
output: DevicePtr,
m: u32,
n: u32,
k: u32,
stream: u64,
) -> Result<()>pub fn dense_gemm(
gpu: &dyn GpuBackend,
kernel: KernelHandle,
input: DevicePtr,
weight: &DenseWeight,
output: DevicePtr,
m: u32,
n: u32,
k: u32,
stream: u64,
) -> Result<()>