Mojo function

naive_blockwise_scaled_fp8_matmul_kernel

naive_blockwise_scaled_fp8_matmul_kernel[c_type: DType, a_type: DType, b_type: DType, a_scales_type: DType, b_scales_type: DType, accum_type: DType, a_layout: Layout, b_layout: Layout, c_layout: Layout, a_scale_layout: Layout, b_scale_layout: Layout, BLOCK_DIM: Int, transpose_b: Bool = False, elementwise_lambda_fn: OptionalReg[fn[dtype: DType, width: Int, *, alignment: Int = 1](IndexList[2], SIMD[dtype, width]) capturing -> None] = OptionalReg[fn[dtype: DType, width: Int, *, alignment: Int = 1](IndexList[2], SIMD[dtype, width]) capturing -> None]({:i1 0, 1}), scales_granularity_mnk: OptionalReg[IndexList[3]] = OptionalReg[IndexList[3]]({:i1 0, 1})](c: LayoutTensor[c_type, c_layout, MutableAnyOrigin], a: LayoutTensor[a_type, a_layout, MutableAnyOrigin], b: LayoutTensor[b_type, b_layout, MutableAnyOrigin], a_scales: LayoutTensor[a_scales_type, a_scale_layout, MutableAnyOrigin], b_scales: LayoutTensor[b_scales_type, b_scale_layout, MutableAnyOrigin])