wassname/pytorch-lightning
1
0
Fork 0
mirror of https://github.com/wassname/pytorch-lightning.git synced 2026-09-11 12:31:23 +08:00
Code Issues Packages Projects Releases Wiki Activity

fixed nccl init

Browse Source
This commit is contained in:
William Falcon
2019-07-12 16:17:50 -04:00
parent 7e54ad3f7c
commit 4f5da45fae
1 changed files with 4 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
pytorch_lightning/models/trainer.py
+4
View File
@@ -381,6 +381,10 @@ class Trainer(TrainerIO):
port = 12910
os.environ['MASTER_PORT'] = f'{port}'
print('-'*100)
print(f'PORT: {port}')
print('-'*100)
sleep(self.proc_rank * 2)
root_node = os.environ['SLURM_NODELIST'].split(' ')[0]