# New Release: Ultralytics v8.4.57

**URL:** <https://community.ultralytics.com/t/new-release-ultralytics-v8-4-57/2015>\
**Category:** Discussion\
**Tags:** ultralytics-official, releases, announcements\
**Created:** [May 30, 2026, 1:33pm UTC](https://community.ultralytics.com/t/new-release-ultralytics-v8-4-57/2015 "2026-05-30T13:33:17Z")\
**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:** [May 30, 2026, 1:33pm UTC](https://community.ultralytics.com/t/new-release-ultralytics-v8-4-57/2015/1 "2026-05-30T13:33:17Z")

</div>

# 🚀 Ultralytics v8.4.57 Released

We’re excited to share **Ultralytics v8.4.57** — a release focused on **Python 3.13 readiness** , **more reliable export workflows** , and a meaningful **RT-DETR CoreML export upgrade**. It also includes a nice quality fix for **semantic segmentation mask alignment** and a broad set of documentation improvements.

If you’re building with **Ultralytics YOLO** , deploying to Apple devices, or preparing for newer Python environments, this release should make things smoother and more predictable. 🙌

## 🌟 Summary

**v8.4.57** is primarily a **stability and compatibility** release rather than a new model release:

- 🐍 **Python 3.13 is now a major CI focus**
- 📤 **Export and slow-test CI are more robust and easier to debug**
- 🍎 **RT-DETR CoreML export is improved**
- 🎯 **Semantic segmentation masks are better aligned**
- 📚 **Docs were refreshed** , including new guides for the **[Ultralytics Platform](https://platform.ultralytics.com)**

## ✨ New Features and Major Improvements

### 🐍 Python 3.13 readiness

This release makes a big step toward smoother support for **Python 3.13** :

- CI testing now targets Python 3.13 across Linux, Windows, macOS, ARM, GPU, and benchmark jobs
- Added official Python 3.13 package support metadata
- Updated dependency constraints for export-related packages including TensorFlow, ONNX, CoreML, NumPy, and protobuf

This should help users moving to newer Python versions see more predictable install and test behavior.

### 📤 More resilient export and CI workflows

A lot of work in this release improves reliability behind the scenes:

- Added a dedicated slow-test runner with clearer diagnostics
- CI now captures more helpful logs for crashes, memory issues, and dependency conflicts
- Export tests have better isolation to reduce flaky failures from parallel execution

These changes are especially valuable for maintainers, contributors, and advanced deployment users. 🔍

### 🛡 Clear compatibility guards for unsupported export stacks

Instead of failing mysteriously, unsupported combinations are now blocked or skipped more clearly:

- TensorFlow export is blocked on **macOS + Python 3.13**
- TensorFlow.js export is blocked on **Python 3.13**
- Axelera export is skipped on **Python 3.13**
- DEEPX CI validation remains on **Python 3.12** for now due to upstream wheel availability

That means less trial-and-error and faster debugging. ✅

### 🍎 RT-DETR CoreML export upgrade

One of the biggest model-related improvements in this release is better **RT-DETR CoreML mlprogram** export support:

- RT-DETR-L exports more reliably to CoreML
- Decoder operations were adjusted to reduce FP16 precision drift
- New tests were added to validate the export path

This makes RT-DETR deployment on Apple hardware much more practical. 📱

### 🎯 Better semantic segmentation mask alignment

A subtle but important fix improves segmentation output quality:

- Resolved a mask offset issue caused by sub-pixel `LetterBox` padding
- Masks are now resized more carefully before padding removal
- Results should appear cleaner and better aligned on original images

Users working with segmentation may notice better edge placement and more accurate mask positioning. 🖼

## 📚 Documentation Updates

This release also includes a strong docs refresh:

- New **[Ultralytics Platform documentation](https://docs.ultralytics.com/platform)** integrations content for importing from Ultralytics HUB and Roboflow
- DEEPX docs and branding updates
- Fixes for broken links and inaccurate docs across Comet, TensorRT, Edge TPU, TF.js, ExecuTorch, OBB, and more
- Explorer legacy snippets were updated to use **YOLO11** models that match the pinned package version

For new projects, we continue to recommend **[YOLO26](https://platform.ultralytics.com/ultralytics/yolo26)** as the latest stable Ultralytics model, with **[YOLO11](https://platform.ultralytics.com/ultralytics/yolo11)** still fully supported for existing workflows.

## 🔧 What Changed

- [Enable RT-DETR CoreML export and protect decoder ops from FP16 drift](https://github.com/ultralytics/ultralytics/pull/24510) by [@artest08](https://github.com/artest08)
- [docs: Fixing text for DEEPX brand rules & guidlines](https://github.com/ultralytics/ultralytics/pull/24535) by [@deepx-dgkim](https://github.com/deepx-dgkim)
- [Fix semantic segmentation mask offset from sub-pixel LetterBox padding](https://github.com/ultralytics/ultralytics/pull/24619) by [@lmycross](https://github.com/lmycross)
- [Fix race condition in `test_export`](https://github.com/ultralytics/ultralytics/pull/24609) by [@Laughing-q](https://github.com/Laughing-q)
- [Fix 404 links in Comet and TensorRT docs](https://github.com/ultralytics/ultralytics/pull/24634) by [@glenn-jocher](https://github.com/glenn-jocher)
- [Add DEEPX vs PyTorch benchmarks pic](https://github.com/ultralytics/ultralytics/pull/24636) by [@lakshanthad](https://github.com/lakshanthad)
- [Correct OBB angle range note in docs](https://github.com/ultralytics/ultralytics/pull/24534) by [@raimbekovm](https://github.com/raimbekovm)
- [Improve readability of distance calculation documentation](https://github.com/ultralytics/ultralytics/pull/24625) by [@Sunny11092003](https://github.com/Sunny11092003)
- [Fix classify CustomizedValidator example augmenting the val set](https://github.com/ultralytics/ultralytics/pull/24532) by [@raimbekovm](https://github.com/raimbekovm)
- [Use `yolo11n` in explorer legacy snippets to match 8.3.11 pin](https://github.com/ultralytics/ultralytics/pull/24548) by [@raimbekovm](https://github.com/raimbekovm)
- [Change CI OS from `cpu-latest` to `ubuntu-latest`](https://github.com/ultralytics/ultralytics/pull/24641) by [@glenn-jocher](https://github.com/glenn-jocher)
- [Docs: Platform Integrations](https://github.com/ultralytics/ultralytics/pull/24642) by [@sergiuwaxmann](https://github.com/sergiuwaxmann)
- [`ultralytics 8.4.57` Python 3.13 CI](https://github.com/ultralytics/ultralytics/pull/24640) by [@glenn-jocher](https://github.com/glenn-jocher)

## 🙌 New Contributors

A big thank you to our new contributors:

- [@Sunny11092003](https://github.com/Sunny11092003) for their first contribution in [PR #24625](https://github.com/ultralytics/ultralytics/pull/24625)
- [@deepx-dgkim](https://github.com/deepx-dgkim) for their first contribution in [PR #24535](https://github.com/ultralytics/ultralytics/pull/24535)

## ▶ Try It Out

You can upgrade with:

```bash
pip install -U ultralytics

```

Then explore the latest release in the [v8.4.57 release page](https://github.com/ultralytics/ultralytics/releases/tag/v8.4.57) or browse the full diff in the [full changelog for v8.4.57](https://github.com/ultralytics/ultralytics/compare/v8.4.56...v8.4.57).

## 💬 Feedback

Please give **v8.4.57** a try and let us know how it works in your environment — especially if you’re testing **Python 3.13** , export pipelines, RT-DETR on CoreML, or segmentation workflows. Your feedback helps the whole community improve faster. 🚀