Function _init_dist_slurm

modelscope/utils/torch_utils.py:85–121

Initialize slurm distributed training environment. If argument ``port`` is not specified, then the master port will be system environment variable ``MASTER_PORT``. If ``MASTER_PORT`` is not in system environment variable, then a default port ``29500`` will be used. Args: ba

(backend: str, port: Optional[int] = None)

def _init_dist_slurm(backend: str, port: Optional[int] = None) -> None:
    """Initialize slurm distributed training environment.

    If argument ``port`` is not specified, then the master port will be system
    environment variable ``MASTER_PORT``. If ``MASTER_PORT`` is not in system
    environment variable, then a default port ``29500`` will be used.

    Args:
        backend (str): Backend of torch.distributed.
        port (int, optional): Master port. Defaults to None.
    """
    proc_id = int(os.environ['SLURM_PROCID'])
    ntasks = int(os.environ['SLURM_NTASKS'])
    node_list = os.environ['SLURM_NODELIST']
    num_gpus = torch.cuda.device_count()
    torch.cuda.set_device(proc_id % num_gpus)
    addr = subprocess.getoutput(
        f'scontrol show hostname {node_list} | head -n1')
    # specify master port
    if port is not None:
        os.environ['MASTER_PORT'] = str(port)
    elif 'MASTER_PORT' in os.environ:
        pass  # use MASTER_PORT in the environment variable
    else:
        # if torch.distributed default port(29500) is available
        # then use it, else find a free port
        if _is_free_port(29500):
            os.environ['MASTER_PORT'] = '29500'
        else:
            os.environ['MASTER_PORT'] = str(_find_free_port())
    # use MASTER_ADDR in the environment variable if it already exists
    if 'MASTER_ADDR' not in os.environ:
        os.environ['MASTER_ADDR'] = addr
    os.environ['WORLD_SIZE'] = str(ntasks)
    os.environ['LOCAL_RANK'] = str(proc_id % num_gpus)
    os.environ['RANK'] = str(proc_id)
    dist.init_process_group(backend=backend)


def get_dist_info(group=None) -> Tuple[int, int]: