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: TensorLayout, b_layout: TensorLayout, c_layout: TensorLayout, a_scale_layout: TensorLayout, b_scale_layout: TensorLayout, BLOCK_DIM: Int, transpose_b: Bool = False, elementwise_lambda_fn: Optional[def[dtype: DType, width: Int, *, alignment: Int = 1](IndexList[2], SIMD[dtype, width]) capturing -> None] = None, scales_granularity_mnk: Optional[IndexList[3]] = None](c: TileTensor[c_type, c_layout, MutAnyOrigin], a: TileTensor[a_type, a_layout, ImmutAnyOrigin], b: TileTensor[b_type, b_layout, ImmutAnyOrigin], a_scales: TileTensor[a_scales_type, a_scale_layout, ImmutAnyOrigin], b_scales: TileTensor[b_scales_type, b_scale_layout, ImmutAnyOrigin])