Rooba
/
lightning
mirror of https://github.com/Lightning-AI/lightning.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

fixed nccl init

This commit is contained in:
William Falcon 2019-07-12 16:03:17 -04:00
parent dc87a4fc91
commit e82014ec6c
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
pytorch_lightning/models/trainer.py
View File

@ -383,8 +383,8 @@ class Trainer(TrainerIO):
root_node = os.environ['SLURM_NODELIST'].split(' ')[0] root_node = os.environ['SLURM_NODELIST'].split(' ')[0]
os.environ['MASTER_ADDR'] = root_node os.environ['MASTER_ADDR'] = root_node
os.environ['MASTER_PORT'] = f'{port}' os.environ['MASTER_PORT'] = f'{port}'
# dist.init_process_group("nccl", rank=self.proc_rank, world_size=self.world_size) dist.init_process_group("nccl", rank=self.proc_rank)
dist.init_process_group("nccl") # dist.init_process_group("nccl")
def __run_pretrain_routine(self, model): def __run_pretrain_routine(self, model):
""" """