Skip to content

Commit

Permalink
Merge pull request mala-project#490 from RandomDefaultUser/horovod_lo…
Browse files Browse the repository at this point in the history
…ading_bug

Fixed a bug when loading horovod
  • Loading branch information
RandomDefaultUser authored Oct 19, 2023
2 parents b697f12 + 159f2c5 commit e769d32
Showing 1 changed file with 20 additions and 12 deletions.
32 changes: 20 additions & 12 deletions mala/common/parameters.py
Original file line number Diff line number Diff line change
Expand Up @@ -6,8 +6,10 @@
import pickle
from time import sleep

horovod_available = False
try:
import horovod.torch as hvd
horovod_available = True
except ModuleNotFoundError:
pass
import numpy as np
Expand Down Expand Up @@ -1257,19 +1259,25 @@ def use_horovod(self):

@use_horovod.setter
def use_horovod(self, value):
if value:
hvd.init()
if value is False:
self._use_horovod = False
else:
if horovod_available:
hvd.init()
# Invalidate, will be updated in setter.
set_horovod_status(value)
self.device = None
self._use_horovod = value
self.network._update_horovod(self.use_horovod)
self.descriptors._update_horovod(self.use_horovod)
self.targets._update_horovod(self.use_horovod)
self.data._update_horovod(self.use_horovod)
self.running._update_horovod(self.use_horovod)
self.hyperparameters._update_horovod(self.use_horovod)
else:
parallel_warn("Horovod requested, but not installed found. "
"MALA will operate without horovod only.")

# Invalidate, will be updated in setter.
set_horovod_status(value)
self.device = None
self._use_horovod = value
self.network._update_horovod(self.use_horovod)
self.descriptors._update_horovod(self.use_horovod)
self.targets._update_horovod(self.use_horovod)
self.data._update_horovod(self.use_horovod)
self.running._update_horovod(self.use_horovod)
self.hyperparameters._update_horovod(self.use_horovod)

@property
def device(self):
Expand Down

0 comments on commit e769d32

Please sign in to comment.