fix: Fix auto quantize multi-gpu tests (NVIDIA#629)

## What does this PR do?

**Type of change:** ? Bug fix

**Overview:** ?

move tensor to cpu before gathering

## Usage
<!-- You can potentially add a usage example below. -->

```python
# Add a code snippet demonstrating how to use this
```

## Testing
```
pytest tests/gpu/torch/quantization/plugins/test_megatron.py::test_auto_quantize
```

## 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/No <!--- If No, explain
why. -->
- **Did you write any new necessary tests?**: Yes/No
- **Did you add or update any necessary documentation?**: Yes/No
- **Did you update
[Changelog](https://github.com/NVIDIA/TensorRT-Model-Optimizer/blob/main/CHANGELOG.rst)?**:
Yes/No <!--- Only for new features, API changes, critical bug fixes or
bw breaking changes. -->

## Additional Information
<!-- E.g. related issue. -->

Signed-off-by: Fridah-nv <[email protected]>

Author: Fridah-nv

modelopt/torch/quantization/algorithms.py

@@ -273,12 +273,13 @@ def get_score(self, recipe: QuantRecipe) -> float:
             if parallel_state.expert_model_parallel_group.is_initialized():
                 # TODO: Support expert model parallelism for score estimation
                 warnings.warn("AutoQuantize does not support expert model parallelism yet.")
+            importance = importance.cpu()
             importance = DistributedProcessGroup.get_dist_syncd_obj(
                 importance,
                 [parallel_state.tensor_parallel_group, parallel_state.data_parallel_group],
                 sum,
             )
-            total_score += importance.cpu().item()
+            total_score += importance.item()
         return total_score
 
     def get_cost(self, recipe: QuantRecipe) -> float: