[5620660][ONNX] Remove toposort after quantization (#524)

## What does this PR do?

**Type of change:** Bug fix

**Overview:** Loading the model with ONNX graphsurgeon after
quantization and FP16 conversion results in an ONNX model with FP16
output instead of FP32 even though the Cast_to_fp32 layer was correctly
placed in the graph output. This PR fixes that issue.

## Usage

```python
$ python -m modelopt.onnx.quantization --onnx_path=$MODEL_NAME.onnx --high_precision_dtype=fp16
```

## Testing
See bug 5620660.

## Before your PR is "*Ready for review*"
<!-- If you haven't finished some of the above items you can still open
`Draft` PR. -->

- **Make sure you read and follow [Contributor
guidelines](https://github.com/NVIDIA/TensorRT-Model-Optimizer/blob/main/CONTRIBUTING.md)**
and your commits are signed.
- **Is this change backward compatible?**: Yes
- **Did you write any new necessary tests?**: No
- **Did you add or update any necessary documentation?**: No
- **Did you update
[Changelog](https://github.com/NVIDIA/TensorRT-Model-Optimizer/blob/main/CHANGELOG.rst)?**:
No

Signed-off-by: gcunhase <[email protected]>

Author: gcunhase

modelopt/onnx/quantization/quantize.py

@@ -528,10 +528,6 @@ def quantize(
                 )
             if direct_io_types:
                 onnx_model = remove_graph_input_q(onnx_model)
-            # Sort nodes topologically
-            graph = gs.import_onnx(onnx_model)
-            graph.toposort().cleanup()
-            onnx_model = gs.export_onnx(graph)
         else:
             # Remove redundant cast nodes in the quantized model
             # Note. This is called within the qdq_to_dq function as well