Skip to content

Make quantize_pt2 private and remove external call sites #10683

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
May 6, 2025
Merged

Make quantize_pt2 private and remove external call sites #10683

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
3 changes: 2 additions & 1 deletion backends/cadence/aot/compiler.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -144,7 +144,6 @@ def fuse_pt2(
return converted_graph_module


# Note: this is the one-liner API to quantize and fuse a model.
def quantize_pt2(
model: torch.nn.Module,
inputs: tuple[object, ...],
Expand All @@ -158,6 +157,8 @@ def quantize_pt2(
not, the inputs will be used for calibration instead, which is useful for
unit tests but should not be used for end-to-end use cases.
Returns a GraphModule with the quantized model.
Note: this function should not be called directly in general. Please use
quantize_and_export_to_executorch for most needs.
"""
# Make the model inference mode by calling model.eval()
model.eval()
Expand Down
Loading