pub fn dense_gemm_prefill(
gpu: &dyn GpuBackend,
fallback_kernel: KernelHandle,
pipelined_kernel: KernelHandle,
input: DevicePtr,
weight: &DenseWeight,
output: DevicePtr,
m: u32,
n: u32,
k: u32,
stream: u64,
) -> Result<()>Expand description
2026-09-25: Dense BF16 prefill GEMM: dense_gemm_bf16_pipelined when
pipelined_kernel is loaded, otherwise dense_gemm with
fallback_kernel.