pub fn try_dense_gemv_tc(
gpu: &dyn GpuBackend,
input: DevicePtr,
weight: &DenseWeight,
output: DevicePtr,
m: u32,
n: u32,
k: u32,
out_stride: u32,
stream: u64,
) -> Result<bool>Expand description
2026-09-25: Run C[t] = A[t] @ W^T on a tensor-core entry if the path is
on and the shape routes. Ok(false) means nothing was launched and the
caller must run its own kernel.