# New Release: Ultralytics v8.3.76

**URL:** <https://community.ultralytics.com/t/new-release-ultralytics-v8-3-76/778>\
**Category:** Discussion\
**Tags:** releases, announcements, ultralytics-official\
**Created:** [February 18, 2025, 1:38pm UTC](https://community.ultralytics.com/t/new-release-ultralytics-v8-3-76/778 "2025-02-18T13:38:01Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![glenn-jocher](https://sea1.discourse-cdn.com/flex001/user_avatar/community.ultralytics.com/glenn-jocher/32/83_2.png) [@glenn-jocher](https://community.ultralytics.com/u/glenn-jocher)\
**Post date:** [February 18, 2025, 1:38pm UTC](https://community.ultralytics.com/t/new-release-ultralytics-v8-3-76/778/1 "2025-02-18T13:38:01Z")

</div>

## 🚀 Announcing Ultralytics v8.3.76: Enhanced Dynamic Inference, Tracking, and Documentation 🌟

We’re excited to share the release of **Ultralytics v8.3.76** , packed with significant improvements to model deployment, tracking, and user-friendliness. This update directly addresses community feedback and introduces enhancements to boost efficiency and developer ease. Let’s dive into the highlights! 🎉

* * *

### 🌟 Summary

This release introduces:

- **Improved dynamic batch inference for ONNX models** (with NMS export).
- **A smoother object tracking experience** with key fixes for tensor-based workflows.
- **Better documentation and examples** to help you navigate and utilize these features seamlessly.

* * *

### 📊 Key Changes

#### **Dynamic Batch Improvements**

- Resolved issues with `dynamic=True` and `nms=True` in ONNX exports, allowing dynamic batch size support.
- Introduced input padding during ONNX export to handle varying batch sizes robustly.

#### **Tracking Enhancements**

- Fixed errors when working with `torch` tensors in `model.track()`.
- Integrated better handling of input images with trackers, improving accuracy for tracked objects.

#### **Performance Accuracy**

- Corrected GPU memory conversion errors for accurate VRAM usage logging.

#### **Documentation Updates**

- Standardized formatting across the documentation for clarity.
- Added examples for interpreting predictions across tasks like detection, pose estimation, segmentation, and more.

#### **Other Code Refinements**

- Adjusted log details to display layers without parameters for transparency in the architecture reporting.
- Improved GitHub issue templates for smoother reporting and handling of feature requests vs. bug reports.

* * *

### 🎯 Purpose & Impact

- 🛠 **Enhanced Deployment** : Dynamic input padding ensures seamless ONNX model experiments and deployments.
- 🎥 **Tracking Upgrades** : Developers and end-users benefit from consistent and reliable tracking output.
- 📋 **Accurate Debugging** : Clearer VRAM usage metrics bolster debugging and optimize memory usage.
- 📚 **Developer Empowerment** : Refined docs and practical examples make features more user-friendly.
- 🚀 **Streamlined Efficiency** : Optimized architecture leads to faster and more reliable handling of models.

* * *

### 🆕 Detailed Changes

Here’s the list of PRs included in this release:

- Initialize `model_name` attribute by [@LoveAndHope-dev](https://github.com/LoveAndHope-dev) → [#19224](https://github.com/ultralytics/ultralytics/pull/19224)
- Update results.boxes docs: `boxes.id` may be `None` by [@shankangke](https://github.com/shankangke) → [#19227](https://github.com/ultralytics/ultralytics/pull/19227)
- Fix bytes-to-GB conversion for logged VRAM usage by [@Y-T-G](https://github.com/Y-T-G) → [#19254](https://github.com/ultralytics/ultralytics/pull/19254)
- Use new “Issue Type” in templates by [@Y-T-G](https://github.com/Y-T-G) → [#19257](https://github.com/ultralytics/ultralytics/pull/19257)
- Add [YouTube Tutorial](https://youtu.be/im7xBCnPURg) to docs by [@RizwanMunawar](https://github.com/RizwanMunawar) → [#19265](https://github.com/ultralytics/ultralytics/pull/19265)
- Standardize string formatting in docs by [@lakshanthad](https://github.com/lakshanthad) → [#19276](https://github.com/ultralytics/ultralytics/pull/19276)
- Fix Tensor input errors in `model.track()` by [@Y-T-G](https://github.com/Y-T-G) → [#19278](https://github.com/ultralytics/ultralytics/pull/19278)  
…and many more!

📜 View the **full changelog** here: [compare/v8.3.75…v8.3.76](https://github.com/ultralytics/ultralytics/compare/v8.3.75...v8.3.76).

* * *

### 🎉 Special Thanks

A warm welcome to **[@LoveAndHope-dev](https://github.com/LoveAndHope-dev)**, who made their first contribution in this release! Thank you for being a valuable part of the YOLO community.

* * *

### 💡 Try It Out!

We encourage all users to explore the new features in **v8.3.76**. Whether you’re deploying models in ONNX, refining tracking pipelines, or diving into the updated documentation, we’re excited to hear your thoughts.

Feel free to open a discussion or report issues on our [GitHub repo](https://github.com/ultralytics/ultralytics). Your feedback is invaluable in shaping future releases. 🙏

➡ Download the latest release here: [v8.3.76](https://github.com/ultralytics/ultralytics/releases/tag/v8.3.76).

Thank you for being part of the YOLO journey, and happy experimenting! 😊