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

Jump to bottom

Fix quantized_matmul with 4D inputs #4335

Closed
wants to merge 1 commit into from
Closed

Fix quantized_matmul with 4D inputs #4335

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
15 changes: 9 additions & 6 deletions backends/cadence/aot/compiler.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -76,6 +76,7 @@ def quantize_pt2(
def export_program(
model: torch.nn.Module,
inputs: tuple[object, ...],
dump_graphs: bool = False,
) -> ExportedProgram:
assert isinstance(model, torch.nn.Module), "model should be an nn.Module"

Expand All @@ -99,7 +100,13 @@ def export_program(
torch._C._set_mkldnn_enabled(False)

# else: capture the model and return it.
return export(model, inputs)
expo_program = export(model, inputs)

if dump_graphs:
logging.info("Exported graph:")
expo_program.graph_module.graph.print_tabular()

return expo_program


# Export the model and lower it to an EdgeProgramManager (in edge IR).
Expand All @@ -111,11 +118,7 @@ def export_to_edge(
assert isinstance(model, torch.nn.Module), "model should be an nn.Module"

# Export the model into an ExportedProgram.
expo_program = export_program(model, inputs)

if dump_graphs:
logging.info("Exported graph:")
expo_program.graph_module.graph.print_tabular()
expo_program = export_program(model, inputs, dump_graphs=dump_graphs)

# Call to_edge to convert the graph to edge IR.
# Note: dim_order is skipped (https://github.com/pytorch/executorch/issues/3704)
Expand Down
Loading