# New Release: Ultralytics v8.3.70

**URL:** <https://community.ultralytics.com/t/new-release-ultralytics-v8-3-70/729>\
**Category:** Discussion\
**Tags:** ultralytics-official, releases, announcements\
**Created:** [January 30, 2025, 1:20pm UTC](https://community.ultralytics.com/t/new-release-ultralytics-v8-3-70/729 "2025-01-30T13:20:02Z")\
**Posts on this page:** 2\
**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:** [January 30, 2025, 1:20pm UTC](https://community.ultralytics.com/t/new-release-ultralytics-v8-3-70/729/1 "2025-01-30T13:20:02Z")

</div>

# 🚀 Exciting New Release: Ultralytics YOLO v8.3.70!

Ultralytics is thrilled to announce the release of **YOLO v8.3.70** , packed with powerful enhancements for smoother workflows, expanded hardware compatibility, and usability improvements. 🎉

Dive into what’s new below!

* * *

## 🌟 Summary

The **v8.3.70** update brings:

- **Export enhancements** with added flexibility for dataset configurations.
- **PyTorch 2.6 compatibility** for seamless integration with the latest updates.
- **Granular benchmarking capabilities** for format-specific optimization.
- **NVIDIA DLA support** , enabling low-latency deployment on specialized hardware.
- **Improved `numpy` stability** for consistent performance.
- Updated tutorials and better documentation for user onboarding.

[Explore the full changelog here](https://github.com/ultralytics/ultralytics/compare/v8.3.69...v8.3.70).

* * *

## 📊 Key Changes

### 1️⃣ Sony IMX500 Export Update

- **What’s New** : Added support for the `data` argument in exports to better control dataset configurations and optimize quantization with models in formats like OpenVINO, TensorRT, and TF Lite.
- **PR** : [Add `data` argument to Sony IMX500 export](https://github.com/ultralytics/ultralytics/pull/18852) by @lakshanthad.

### 2️⃣ PyTorch 2.6 Compatibility

- **What’s New** : Updated Torch-Torchvision mappings for compatibility with PyTorch 2.6.
- **PR** : [Update torchvision compatibility table for `torch 2.6`](https://github.com/ultralytics/ultralytics/pull/18935) by @glenn-jocher.

### 3️⃣ Format-Specific Benchmarking

- **What’s New** : Benchmarks can now target specific export formats like ONNX, allowing deeper insights into performance metrics.
- **PR** : [Add support for single export format benchmarking](https://github.com/ultralytics/ultralytics/pull/18740) by @RizwanMunawar.

### 4️⃣ NVIDIA DLA Core Usage

- **What’s New** : Support for running YOLO models on NVIDIA DLA cores for optimized inference on hardware-specific platforms.
- **PR** : [Add DLA-specific core usage](https://github.com/ultralytics/ultralytics/pull/18930) by @AbelHaro.

### 5️⃣ Enhanced CI Stability

- **What’s New** : Pinned `numpy<=2.1.1` to resolve compatibility issues during CI tests for OpenVINO and TensorFlow Lite.
- **PR** : [Pin `numpy` for CI stability](https://github.com/ultralytics/ultralytics/pull/18943) by @lakshanthad.

### 6️⃣ Documentation Refinements

- **What’s New** : Added a new tutorial video and refined docs for clarity—check it out to get started faster!
- **PRs** :
  - [Add video tutorial to docs](https://github.com/ultralytics/ultralytics/pull/18936) by @RizwanMunawar.
  - [Minor Docs edits](https://github.com/ultralytics/ultralytics/pull/18940) by @LexBarou.

* * *

## 🎯 Purpose & Impact

- **Export Workflows** : Empower users with better quantization and deployment control via the new `data` argument during export. Perfect for edge environments.
- **Torch Compatibility** : Stay ahead with PyTorch 2.6’s latest features without breaking workflows.
- **Benchmark Smarter** : Dive deeper into how models perform in export-specific formats for targeted optimizations.
- **Hardware Optimization** : Unlock faster inferences using NVIDIA DLA-specific optimizations for specialized hardware.
- **Fail-Proof `numpy`** : Ensure test stability and robustness during development and CI.
- **User-Friendly Docs** : Learn faster with clearer visuals and refined templates.

* * *

## 📝 What’s Changed

- [Update torchvision compatibility table for `torch 2.6`](https://github.com/ultralytics/ultralytics/pull/18935) by @glenn-jocher.
- [Add YouTube tutorial to docs](https://github.com/ultralytics/ultralytics/pull/18936) by @RizwanMunawar.
- [Single export format benchmarking](https://github.com/ultralytics/ultralytics/pull/18740) by @RizwanMunawar.
- [Sony IMX500 `data` for export](https://github.com/ultralytics/ultralytics/pull/18852) by @lakshanthad.
- [Add DLA-specific core support](https://github.com/ultralytics/ultralytics/pull/18930) by @AbelHaro.
- [Pin `numpy` version for CI stability](https://github.com/ultralytics/ultralytics/pull/18943) by @lakshanthad.
- [Minor Documentation tweaks](https://github.com/ultralytics/ultralytics/pull/18940) by @LexBarou.

### 🥳 New Contributors

We’re excited to welcome new contributors to the community:

- @LexBarou: [Minor Docs edits](https://github.com/ultralytics/ultralytics/pull/18940).
- @AbelHaro: [Add DLA specific core usage](https://github.com/ultralytics/ultralytics/pull/18930).

* * *

## 📥 Ready to Try?

Update to **v8.3.70** today and take advantage of these improvements:

```bash
pip install ultralytics --upgrade

```

We’d love to hear your feedback—jump into [Discussions](https://github.com/ultralytics/ultralytics/discussions) or report any issues on [GitHub](https://github.com/ultralytics/ultralytics/issues).

Thank you for your continued support in building an amazing YOLO community. 🙌

[Release Details](https://github.com/ultralytics/ultralytics/releases/tag/v8.3.70) | [Full Changelog](https://github.com/ultralytics/ultralytics/compare/v8.3.69...v8.3.70)

---

<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:** [January 30, 2025, 7:15pm UTC](https://community.ultralytics.com/t/new-release-ultralytics-v8-3-70/729/2 "2025-01-30T19:15:13Z")

</div>

PyTorch 2.6.0!!