# New Release: Ultralytics v8.4.92

**URL:** https://community.ultralytics.com/t/new-release-ultralytics-v8-4-92/2103
**Category:** Discussion
**Tags:** announcements, ultralytics-official, releases
**Created:** [July 10, 2026, 1:39pm UTC](https://community.ultralytics.com/t/new-release-ultralytics-v8-4-92/2103 "2026-07-10T13:39:59Z")
**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: [July 10, 2026, 1:39pm UTC](https://community.ultralytics.com/t/new-release-ultralytics-v8-4-92/2103/1 "2026-07-10T13:39:59Z")

</div>

# 🚀 Ultralytics v8.4.92 Released

Ultralytics v8.4.92 improves **RKNN INT8 multi-batch export reliability** , strengthens compiled inference and dataset validation, preserves segmentation boxes near image boundaries, and expands **YOLO26 web deployment documentation**. 🌐

Review the [v8.4.92 release on GitHub](https://github.com/ultralytics/ultralytics/releases/tag/v8.4.92) for the complete release details.

## 🌟 New Features and Documentation

### YOLO26 deployment with LiteRT.js

Browser and Node.js deployment documentation now covers the official [`@ultralytics/yolo` NPM package](https://www.npmjs.com/package/@ultralytics/yolo), including WebGPU acceleration, CPU/WASM fallback, and support for all six YOLO26 tasks.

Install the packages with:

```bash
npm i @ultralytics/yolo @litertjs/core

```

This update was contributed in [PR #25087](https://github.com/ultralytics/ultralytics/pull/25087) by [@onuralpszr](https://github.com/onuralpszr).

### Refreshed pose dataset documentation

Documentation for COCO-Pose, COCO8-Pose, Dog-Pose, Hand Keypoints, and Tiger-Pose now includes more accurate dataset sizes, splits, keypoint details, and download requirements. It also provides clearer guidance for annotating and training custom pose datasets with [Ultralytics Platform](https://platform.ultralytics.com/).

COCO-Pose users should plan for approximately **27 GB** for the complete initial download.

These improvements arrived in [PR #25062](https://github.com/ultralytics/ultralytics/pull/25062) from [@raimbekovm](https://github.com/raimbekovm).

## 🔧 Bug Fixes

### Reliable RKNN INT8 multi-batch export

RKNN calibration now uses a batch-1 ONNX graph while passing the requested inference batch through `rknn_batch_size`. This resolves failures with configurations such as `batch=8` and adds regression coverage for calibration and runtime batch handling.

See [PR #25094](https://github.com/ultralytics/ultralytics/pull/25094) by [@glenn-jocher](https://github.com/glenn-jocher) for the implementation.

### Safer compiled model reuse

Predictor initialization now explicitly checks whether the model is `None`, preventing `torch.compile` wrappers from triggering unsupported truth-value checks during repeated inference.

The fix is included in [PR #25092](https://github.com/ultralytics/ultralytics/pull/25092) by [@glenn-jocher](https://github.com/glenn-jocher).

### Correct validation split handling

Dataset validation now checks the split requested by the user, such as `val` or `test`, rather than always checking `val`. Missing splits produce a clear error instead of silently falling back to another split.

This behavior was corrected in [PR #25093](https://github.com/ultralytics/ultralytics/pull/25093) by [@glenn-jocher](https://github.com/glenn-jocher).

### Better polygon-to-box conversion

`segment2box()` now preserves the visible portion of polygons crossing image boundaries. This reduces shrunken or collapsed boxes after perspective and related augmentations.

The update was contributed through [PR #25086](https://github.com/ultralytics/ultralytics/pull/25086) by [@JESUSROYETH](https://github.com/JESUSROYETH).

## 🛠 Workflow Improvements

The contributor license workflow now uses the shared [`ultralytics/actions`](https://github.com/ultralytics/actions) workflow, reducing duplicated configuration and limiting workflow permissions.

This change was made in [PR #25084](https://github.com/ultralytics/ultralytics/pull/25084) by [@glenn-jocher](https://github.com/glenn-jocher).

## 📦 Get v8.4.92

Upgrade to the latest release with:

```bash
pip install -U ultralytics

```

You can inspect every change in the [v8.4.91 to v8.4.92 comparison](https://github.com/ultralytics/ultralytics/compare/v8.4.91...v8.4.92) before updating.

Give v8.4.92 a try and let us know how the improved RKNN export, validation, augmentation, compiled inference, and YOLO26 web deployment workflows perform in your projects. Thanks to all contributors and the wider YOLO community for helping make this release possible! 🙌