Skip to content

fix more thread tasks without proper ctx #1931

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

Merged
merged 1 commit into from
Sep 26, 2025
Merged

fix more thread tasks without proper ctx #1931

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
2 changes: 2 additions & 0 deletions gptqmodel/looper/module_looper.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -450,6 +450,7 @@ def loop(self, fail_safe: bool = False, **kwargs):
with ThreadPoolExecutor(max_workers=max_workers) as executor:
futures = []

@torch.inference_mode()
def process_module(name, m):
# prevent cuda sync memory ctx bugs
m_device = get_device(m)
Expand Down Expand Up @@ -541,6 +542,7 @@ def process_module(name, m):
torch_sync()
for reverse_p in reversed(self.processors):
for name in processed_subset:
@torch.inference_mode()
def finalize_module(module):
# prevent cuda sync memory ctx bugs
m_device = get_device(module)
Expand Down
2 changes: 1 addition & 1 deletion tests/test_qqq_inference.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,4 +5,4 @@
framework=EVAL.LM_EVAL,
tasks=[EVAL.LM_EVAL.ARC_CHALLENGE])

print(f"{eval_results}")
print(f"{eval_results}")