Former-commit-id: 8792d78c82e83f319c584079d7ebfa2dccbb346a
This commit is contained in:
hiyouga 2024-11-24 23:56:21 +08:00
parent 5a7ff02806
commit a04538e70b

View File

@ -95,7 +95,8 @@ def main():
(
"torchrun --nnodes {nnodes} --node_rank {node_rank} --nproc_per_node {nproc_per_node} "
"--master_addr {master_addr} --master_port {master_port} {file_name} {args}"
).format(
)
.format(
nnodes=os.getenv("NNODES", "1"),
node_rank=os.getenv("NODE_RANK", "0"),
nproc_per_node=os.getenv("NPROC_PER_NODE", str(get_device_count())),
@ -103,8 +104,8 @@ def main():
master_port=master_port,
file_name=launcher.__file__,
args=" ".join(sys.argv[1:]),
),
shell=True,
)
.split()
)
sys.exit(process.returncode)
else: