Skip to content

Cache backend FakeTensor dispatches during ExportPass replay (#21700) #21700

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

Open
apullin wants to merge 2 commits into
base: main
Choose a base branch
from
+457 −8
Open

Cache backend FakeTensor dispatches during ExportPass replay (#21700) #21700

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
308abbf
Fast-copy cold nodes during ExportPass retracing
apullin Aug 10, 2026
173c7bd
Cache backend FakeTensor dispatches during ExportPass replay (#21700)
apullin Aug 10, 2026
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 backends/arm/_passes/arm_pass.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -140,6 +140,8 @@ def call_submodule(
self.submodule_depth += 1
if self.submodule_depth == 1:
result = super().call_submodule(graph_module, inputs)
elif self.should_run_pass(graph_module):
result = super().call_submodule(graph_module, inputs)
else:
# When we trace a submodule, we don't want to apply the calling pass.
# Temporarily replace call_operator to avoid this.
Expand Down
Loading
Loading