Mojo function

dual_gemv_kernel

dual_gemv_kernel[c_type: DType, c_shape: DimList, a_type: DType, a_shape: DimList, b_type: DType, b_shape: DimList, simd_width: UInt, tile_m: UInt, tile_n: UInt, num_threads: UInt, binary_lambda_fn: fn[DType, Int](SIMD[$0, $1], SIMD[$0, $1]) -> SIMD[$0, $1], elementwise_lambda_fn: OptionalReg[fn[DType, Int, Int](IndexList[2], SIMD[$0, $1]) capturing -> None] = OptionalReg[fn[DType, Int, Int](IndexList[2], SIMD[$0, $1]) capturing -> None]({:i1 0, 1}), s_type: DType = get_accum_type[::DType,::DType]()](c: NDBuffer[c_type, 2, MutableAnyOrigin, c_shape], a: NDBuffer[a_type, 2, MutableAnyOrigin, a_shape], b0: NDBuffer[b_type, 2, MutableAnyOrigin, b_shape], b1: NDBuffer[b_type, 2, MutableAnyOrigin, b_shape])