Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fix XGLM OOM on CI #24123

Merged
merged 1 commit into from
Jun 9, 2023
Merged

Fix XGLM OOM on CI #24123

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions tests/models/xglm/test_modeling_tf_xglm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,7 @@

from __future__ import annotations

import gc
import unittest

from transformers import XGLMConfig, XGLMTokenizer, is_tf_available
Expand Down Expand Up @@ -190,6 +191,11 @@ def test_resize_token_embeddings(self):

@require_tf
class TFXGLMModelLanguageGenerationTest(unittest.TestCase):
def tearDown(self):
super().tearDown()
# clean-up as much as possible GPU memory occupied by PyTorch
gc.collect()

@slow
def test_lm_generate_xglm(self, verify_outputs=True):
model = TFXGLMForCausalLM.from_pretrained("facebook/xglm-564M")
Expand Down
7 changes: 7 additions & 0 deletions tests/models/xglm/test_modeling_xglm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,6 +14,7 @@
# limitations under the License.

import datetime
import gc
import math
import unittest

Expand Down Expand Up @@ -349,6 +350,12 @@ def test_model_from_pretrained(self):

@require_torch
class XGLMModelLanguageGenerationTest(unittest.TestCase):
def tearDown(self):
super().tearDown()
# clean-up as much as possible GPU memory occupied by PyTorch
gc.collect()
torch.cuda.empty_cache()

def _test_lm_generate_xglm_helper(
self,
gradient_checkpointing=False,
Expand Down