pub fn matmul_dispatch(
a: &[f32],
a_rows: usize,
a_cols: usize,
b: &[f32],
b_rows: usize,
b_cols: usize,
mode: SimdMode,
) -> Result<Vec<f32>, EngineError>Expand description
Dispatch scalar vs Neon (blocked) paths. Neon is available on all targets for parity tests;
on aarch64 this is the production SIMD entry (intrinsics may replace the body later).