Mojo function

grouped_matmul_sm100_blockwise_scaled_fp8

grouped_matmul_sm100_blockwise_scaled_fp8[c_type: DType, a_type: DType, b_type: DType, a_scales_type: DType, b_scales_type: DType, a_offsets_type: DType, expert_ids_type: DType, transpose_b: Bool, //, *, config: MatmulConfig[a_type, b_type, c_type, transpose_b], elementwise_lambda_fn: Optional[def[dtype: DType, width: Int, *, alignment: Int = 1](IndexList[2], SIMD[dtype, width]) capturing -> None] = None](c: TileTensor[c_type, c.LayoutType, c.origin, linear_idx_type=c.linear_idx_type, element_size=c.element_size], a: TileTensor[a_type, a.LayoutType, a.origin, linear_idx_type=a.linear_idx_type, element_size=a.element_size], b: TileTensor[b_type, b.LayoutType, b.origin, linear_idx_type=b.linear_idx_type, element_size=b.element_size], a_scales: TileTensor[a_scales_type, a_scales.LayoutType, a_scales.origin, linear_idx_type=a_scales.linear_idx_type, element_size=a_scales.element_size], b_scales: TileTensor[b_scales_type, b_scales.LayoutType, b_scales.origin, linear_idx_type=b_scales.linear_idx_type, element_size=b_scales.element_size], a_offsets: TileTensor[a_offsets_type, a_offsets.LayoutType, a_offsets.origin, linear_idx_type=a_offsets.linear_idx_type, element_size=a_offsets.element_size], expert_ids: TileTensor[expert_ids_type, expert_ids.LayoutType, expert_ids.origin, linear_idx_type=expert_ids.linear_idx_type, element_size=expert_ids.element_size], max_num_tokens_per_expert: Int, num_active_experts: Int, ctx: DeviceContext)