Mojo function

grouped_matmul_1d2d_blockwise_fp8

grouped_matmul_1d2d_blockwise_fp8[a_scales_type: DType, b_scales_type: DType, transpose_b: Bool, //, *, config: MatmulConfig[config.a_type, config.b_type, config.c_type, transpose_b]](c_device: TileTensor[c_device.dtype, c_device.LayoutType, c_device.origin, address_space=c_device.address_space, linear_idx_type=c_device.linear_idx_type, element_size=c_device.element_size], a_device: TileTensor[a_device.dtype, a_device.LayoutType, a_device.origin, address_space=a_device.address_space, linear_idx_type=a_device.linear_idx_type, element_size=a_device.element_size], b_device: TileTensor[b_device.dtype, b_device.LayoutType, b_device.origin, address_space=b_device.address_space, linear_idx_type=b_device.linear_idx_type, element_size=b_device.element_size], a_scales: TileTensor[a_scales.dtype, a_scales.LayoutType, a_scales.origin, address_space=a_scales.address_space, linear_idx_type=a_scales.linear_idx_type, element_size=a_scales.element_size], b_scales: TileTensor[b_scales.dtype, b_scales.LayoutType, b_scales.origin, address_space=b_scales.address_space, linear_idx_type=b_scales.linear_idx_type, element_size=b_scales.element_size], a_offsets: TileTensor[a_offsets.dtype, a_offsets.LayoutType, a_offsets.origin, address_space=a_offsets.address_space, linear_idx_type=a_offsets.linear_idx_type, element_size=a_offsets.element_size], expert_ids: TileTensor[expert_ids.dtype, expert_ids.LayoutType, expert_ids.origin, address_space=expert_ids.address_space, linear_idx_type=expert_ids.linear_idx_type, element_size=expert_ids.element_size], expert_scales: TileTensor[expert_scales.dtype, expert_scales.LayoutType, expert_scales.origin, address_space=expert_scales.address_space, linear_idx_type=expert_scales.linear_idx_type, element_size=expert_scales.element_size], num_active_experts: Int, ctx: DeviceContext)