src/accelerate/utils/launch.py [219:277]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        args.nproc_per_node = str(num_processes // num_machines)
        args.nnodes = str(num_machines)
        args.node_rank = int(args.machine_rank)
        if getattr(args, "same_network", False):
            args.master_addr = str(main_process_ip)
            args.master_port = str(main_process_port)
        else:
            args.rdzv_endpoint = f"{main_process_ip}:{main_process_port}"
    else:
        args.nproc_per_node = str(num_processes)
        if main_process_port is not None:
            args.master_port = str(main_process_port)

    # only need to check port availability in main process, in case we have to start multiple launchers on the same machine
    # for some reasons like splitting log files.
    need_port_check = num_machines <= 1 or int(args.machine_rank) == 0
    if need_port_check and is_port_in_use(main_process_port):
        if num_machines <= 1:
            args.standalone = True
            warnings.warn(
                f"Port `{main_process_port}` is already in use. "
                "Accelerate will attempt to launch in a standalone-like mode by finding an open port automatically for this session. "
                "If this current attempt fails, or for more control in future runs, please specify a different port "
                "(e.g., `--main_process_port <your_chosen_port>`) or use `--main_process_port 0` for automatic selection "
                "in your launch command or Accelerate config file."
            )
        else:
            raise ConnectionError(
                f"Tried to launch distributed communication on port `{main_process_port}`, but another process is utilizing it. "
                "Please specify a different port (such as using the `--main_process_port` flag or specifying a different `main_process_port` in your config file)"
                " and rerun your script. To automatically use the next open port (on a single node), you can set this to `0`."
            )

    if args.module and args.no_python:
        raise ValueError("--module and --no_python cannot be used together")
    elif args.module:
        args.module = True
    elif args.no_python:
        args.no_python = True

    current_env = os.environ.copy()
    if args.debug:
        current_env["ACCELERATE_DEBUG_MODE"] = "true"
    gpu_ids = getattr(args, "gpu_ids", "all")
    if gpu_ids != "all" and args.gpu_ids is not None:
        if is_xpu_available():
            current_env["ZE_AFFINITY_MASK"] = gpu_ids
        elif is_mlu_available():
            current_env["MLU_VISIBLE_DEVICES"] = gpu_ids
        elif is_sdaa_available():
            current_env["SDAA_VISIBLE_DEVICES"] = gpu_ids
        elif is_musa_available():
            current_env["MUSA_VISIBLE_DEVICES"] = gpu_ids
        elif is_npu_available():
            current_env["ASCEND_RT_VISIBLE_DEVICES"] = gpu_ids
        elif is_hpu_available():
            current_env["HABANA_VISIBLE_MODULES"] = gpu_ids
        else:
            current_env["CUDA_VISIBLE_DEVICES"] = gpu_ids
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



src/accelerate/utils/launch.py [412:470]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        args.nproc_per_node = str(num_processes // num_machines)
        args.nnodes = str(num_machines)
        args.node_rank = int(args.machine_rank)
        if getattr(args, "same_network", False):
            args.master_addr = str(main_process_ip)
            args.master_port = str(main_process_port)
        else:
            args.rdzv_endpoint = f"{main_process_ip}:{main_process_port}"
    else:
        args.nproc_per_node = str(num_processes)
        if main_process_port is not None:
            args.master_port = str(main_process_port)

    # only need to check port availability in main process, in case we have to start multiple launchers on the same machine
    # for some reasons like splitting log files.
    need_port_check = num_machines <= 1 or int(args.machine_rank) == 0
    if need_port_check and is_port_in_use(main_process_port):
        if num_machines <= 1:
            args.standalone = True
            warnings.warn(
                f"Port `{main_process_port}` is already in use. "
                "Accelerate will attempt to launch in a standalone-like mode by finding an open port automatically for this session. "
                "If this current attempt fails, or for more control in future runs, please specify a different port "
                "(e.g., `--main_process_port <your_chosen_port>`) or use `--main_process_port 0` for automatic selection "
                "in your launch command or Accelerate config file."
            )
        else:
            raise ConnectionError(
                f"Tried to launch distributed communication on port `{main_process_port}`, but another process is utilizing it. "
                "Please specify a different port (such as using the `--main_process_port` flag or specifying a different `main_process_port` in your config file)"
                " and rerun your script. To automatically use the next open port (on a single node), you can set this to `0`."
            )

    if args.module and args.no_python:
        raise ValueError("--module and --no_python cannot be used together")
    elif args.module:
        args.module = True
    elif args.no_python:
        args.no_python = True

    current_env = os.environ.copy()
    if args.debug:
        current_env["ACCELERATE_DEBUG_MODE"] = "true"
    gpu_ids = getattr(args, "gpu_ids", "all")
    if gpu_ids != "all" and args.gpu_ids is not None:
        if is_xpu_available():
            current_env["ZE_AFFINITY_MASK"] = gpu_ids
        elif is_mlu_available():
            current_env["MLU_VISIBLE_DEVICES"] = gpu_ids
        elif is_sdaa_available():
            current_env["SDAA_VISIBLE_DEVICES"] = gpu_ids
        elif is_musa_available():
            current_env["MUSA_VISIBLE_DEVICES"] = gpu_ids
        elif is_npu_available():
            current_env["ASCEND_RT_VISIBLE_DEVICES"] = gpu_ids
        elif is_hpu_available():
            current_env["HABANA_VISIBLE_MODULES"] = gpu_ids
        else:
            current_env["CUDA_VISIBLE_DEVICES"] = gpu_ids
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -