Mojo function

multistage_dual_gemm

multistage_dual_gemm[c_type: DType, c_layout: Layout, a_type: DType, a_layout: Layout, b_type: DType, b_layout: Layout, //, transpose_b: Bool, config: MatmulConfig[a_type, b_type, c_type, transpose_b], binary_lambda_fn: fn[DType, Int](SIMD[$0, $1], SIMD[$0, $1]) -> SIMD[$0, $1] = swilu[::DType,::Int], 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})](c: LayoutTensor[c_type, c_layout, origin], a: LayoutTensor[a_type, a_layout, origin], b0: LayoutTensor[b_type, b_layout, origin], b1: LayoutTensor[b_type, b_layout, origin], ctx: DeviceContext)

multistage_dual_gemm[c_type: DType, c_shape: DimList, a_type: DType, a_shape: DimList, b_type: DType, b_shape: DimList, //, *, transpose_b: Bool, config: MatmulConfig[a_type, b_type, c_type, transpose_b], binary_lambda_fn: fn[DType, Int](SIMD[$0, $1], SIMD[$0, $1]) -> SIMD[$0, $1] = swilu[::DType,::Int], 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}), num_k_partitions: Int = 1](c: NDBuffer[c_type, 2, origin, c_shape], a: NDBuffer[a_type, 2, origin, a_shape], b0: NDBuffer[b_type, 2, origin, b_shape], b1: NDBuffer[b_type, 2, origin, b_shape], ctx: DeviceContext)