INNER CODE UNIT · Python

print

huggingface/large_language_model_training_playbook · debug/torch-distributed-gpu-test.py:56

def print(*args, **kwargs):
    """ solves multi-process interleaved print problem """
    with open(__file__, "r") as fh:
        fcntl.flock(fh, fcntl.LOCK_EX)
        try:
            builtins.print(*args, **kwargs)
        finally:
            fcntl.flock(fh, fcntl.LOCK_UN)

local_rank = int(os.environ["LOCAL_RANK"])
torch.cuda.set_device(local_rank)
device = torch.device("cuda", local_rank)
hostname = socket.gethostname()

gpu = f"[{hostname}-{local_rank}]"

try:
    # test distributed

View source record →