Move apply_torch_ops_passes() to _lower_ep_to_edge().

Summary: Make apply_torch_ops_passes() called by quantization API too. Previously quantize_and_export_to_edge() was not picking it up.

Differential Revision: D78852189

Author: eigen-k

backends/cadence/aot/compiler.py

@@ -233,6 +233,9 @@ def _lower_ep_to_edge(
     """
     Lower an ExportedProgram to an EdgeProgramManager (in edge IR).
     """
+    # Apply passes which transform the ExportedProgram before it gets lowered to edge.
+    expo_program = apply_torch_ops_passes(expo_program)
+
     # Call to_edge to convert the graph to edge IR.
     # Note: dim_order is skipped (https://github.com/pytorch/executorch/issues/3704)
     edge_prog_manager = to_edge(
@@ -268,9 +271,6 @@ def export_to_edge(
     # Export the model into an ExportedProgram.
     expo_program = trace(model, inputs)
 
-    # Apply passes which transform the ExportedProgram before it gets lowered to edge.
-    expo_program = apply_torch_ops_passes(expo_program)
-
     # Lower the model to edge IR.
     edge_prog_manager = _lower_ep_to_edge(
         expo_program, dump_graphs, constant_methods, core_aten_exceptions