# New Release: Ultralytics v8.3.244

**URL:** <https://community.ultralytics.com/t/new-release-ultralytics-v8-3-244/1722>\
**Category:** Discussion\
**Tags:** releases, announcements, ultralytics-official\
**Created:** [December 31, 2025, 1:14pm UTC](https://community.ultralytics.com/t/new-release-ultralytics-v8-3-244/1722 "2025-12-31T13:14:26Z")\
**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:** [December 31, 2025, 1:14pm UTC](https://community.ultralytics.com/t/new-release-ultralytics-v8-3-244/1722/1 "2025-12-31T13:14:26Z")

</div>

## 🚀 Ultralytics v8.3.244 is out!

**TL;DR:** YOLO inference is now _safer_ in long-running apps when switching `device=` (CPU ↔ GPU) between `predict()` calls—Ultralytics will automatically reset the predictor to avoid stale state issues 🔄🖥✅

You can view the release details as part of the [v8.3.244 GitHub release](https://github.com/ultralytics/ultralytics/releases/tag/v8.3.244) and browse the [full changelog from v8.3.243 to v8.3.244](https://github.com/ultralytics/ultralytics/compare/v8.3.243...v8.3.244).

* * *

## 🌟 New Features (Main Update)

### 🔁 Predictor reset on device change

When `device=` changes between `predict()` calls, Ultralytics now re-initializes `self.predictor` instead of reusing a predictor tied to the previous device.

- PR: [Reset YOLO predictor on device change](https://github.com/ultralytics/ultralytics/pull/23086) by [@Y-T-G](https://github.com/Y-T-G)

**Why it matters:** In real services and notebooks where you may alternate between `device="cpu"` and `device=0`, you won’t accidentally “carry over” device-specific predictor state.

Minimal usage example:

```python
from ultralytics import YOLO

model = YOLO("yolo11n.pt")
model.predict("image.jpg", device="cpu")
model.predict("image.jpg", device=0) # predictor safely resets when device changes

```

* * *

## 📦 Improvements

### 🐳🧩 ExecuTorch export dependency fix for ARM64 Docker

A broad `setuptools<71.0.0` workaround was removed and replaced with a targeted requirement: on **Linux + ARM64 + Docker** , require `packaging>=22.0` to avoid build/export issues.

- PR: [Remove setuptools check\_requirements in ExecuTorch export](https://github.com/ultralytics/ultralytics/pull/23064) by [@onuralpszr](https://github.com/onuralpszr)

* * *

## 🛠 Reliability + Polish

### 🐳 Docker build improvements

Cleaner, more reproducible Docker builds with less layer bloat and more consistent installs.

- PR: [Dockerfile improvements](https://github.com/ultralytics/ultralytics/pull/23090) by [@glenn-jocher](https://github.com/glenn-jocher)

### 📚 Examples/tests hardening + YAML fixes

Includes robustness tweaks (notably in example integrations) plus small config/documentation wording cleanup (including references updated to **YOLO11** ).

- PR: [YAML fixes](https://github.com/ultralytics/ultralytics/pull/23092) by [@glenn-jocher](https://github.com/glenn-jocher)

* * *

## ✅ How to try it

Upgrade:

```bash
pip install -U ultralytics

```

Then run a quick check:

```bash
yolo predict model=yolo11n.pt source=https://ultralytics.com/images/bus.jpg

```

* * *

## 💬 Feedback welcome

If you hit any edge cases (especially with device switching in long-lived processes, ARM64 Docker exports, or example builds), please share your repro details in the community—your reports help keep Ultralytics YOLO rock-solid for everyone 🙌