[dynamo exporter] Add optimize to onnx conversion config (#1622)

## Describe your changes

## Checklist before requesting a review
- [ ] Add unit tests for this change.
- [ ] Make sure all tests can pass.
- [ ] Update documents if necessary.
- [ ] Lint and apply fixes to your code by running `lintrunner -a`
- [ ] Is this a user-facing change? If yes, give a description of this
change to be included in the release notes.
- [ ] Is this PR including examples changes? If yes, please remember to
update [example
documentation](https://github.com/microsoft/Olive/blob/main/docs/source/examples.md)
in a follow-up PR.

## (Optional) Issue link

olive/passes/onnx/conversion.py

@@ -103,6 +103,11 @@ def _default_config(cls, accelerator_spec: AcceleratorSpec) -> Dict[str, PassCon
                     "Includes config.json, generation_config.json, and tokenizer related files."
                 ),
             ),
+            "optimize": PassConfigParam(
+                type_=bool,
+                default_value=True,
+                description=("Whether to export the model with constant folding and redundancies elimination."),
+            ),
             "dynamic": PassConfigParam(
                 type_=bool, default_value=True, description=("Whether to export the model with dynamic axes/shapes.")
             ),
@@ -263,6 +268,7 @@ def _export_pytorch_model(
                         dynamic_shapes=io_config.dynamic_shapes,
                         dynamo=True,
                         fallback=True,
+                        optimize=config.optimize,
                         report=logger.isEnabledFor(logging.DEBUG),
                     )
                     assert onnx_program is not None