Bias running average computation in float (#738)

## What does this PR do?

**Type of change:**  Bug fix

**Overview:** ?
Computing Bias running average with bf16 creates incorrect estimations.
Impact on accuracy for Qwen2.5-7B model:

With BF16 running average:

NVFP4_AFFINE_KV | 59.11%
-- | --

With running average in Float:
NVFP4_AFFINE_KV | 71.81%
-- | --


## Usage
Use examples/lm_eval/mmlu.py with batchsize of 1
Note: the issue is masked with larger batch sizes

## Testing
- Ran mmlu benchmark with mmlu.py and nv-eval
- also ploted bf16 and float running average for different layers, one
of the example for layer 0 in Qwen2.5-7B:
 
<img width="2100" height="600" alt="image"
src="https://github.com/user-attachments/assets/715059c5-34a4-495e-b6f1-0b57cf0c08af"
/>

Note: for the larger value bf16 shows smaller value compared to float

## 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/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?**: NA
- **Did you update
[Changelog](https://github.com/NVIDIA/Model-Optimizer/blob/main/CHANGELOG.rst)?**:
NA

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

Signed-off-by: Kinjal Patel <kinjalpravin@nvidia.com>

Author: kinjalpatel27

modelopt/torch/quantization/calib/bias.py

@@ -134,7 +134,13 @@ def collect(self, x: torch.Tensor):
             if self._calib_bias is None:
                 self._calib_bias = bias_
             else:
-                self._calib_bias = (self._calib_bias * self._cnt + bias_) / (self._cnt + 1)
+                dtype = bias_.dtype
+                # Convert bias to float for numerical stability
+                self._calib_bias = (self._calib_bias.float() * self._cnt + bias_.float()) / (
+                    self._cnt + 1
+                )
+                self._calib_bias = self._calib_bias.to(dtype)
+
             self._cnt += 1
         elif self._method == "max_min":
             max_, min_ = compute_maxmin(x, self._axis)