# New Release: Ultralytics v8.4.156

**URL:** <https://community.ultralytics.com/t/new-release-ultralytics-v8-4-156/2226>\
**Category:** Discussion\
**Tags:** ultralytics-official, releases, announcements\
**Created:** [September 20, 2026, 1:08pm UTC](https://community.ultralytics.com/t/new-release-ultralytics-v8-4-156/2226 "2026-09-20T13:08:16Z")\
**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:** [September 20, 2026, 1:08pm UTC](https://community.ultralytics.com/t/new-release-ultralytics-v8-4-156/2226/1 "2026-09-20T13:08:16Z")

</div>

# 🚀 Ultralytics v8.4.156: Reliable NDJSON Datasets and Faster INT8 TensorRT

Ultralytics v8.4.156 is now available! This release improves remote NDJSON dataset reliability, accelerates INT8 TensorRT exports while preserving accuracy, and strengthens cross-platform testing. 🌟

## 🔄 Dataset Reliability

Remote NDJSON conversion is now safer and more efficient thanks to [PR #26242](https://github.com/ultralytics/ultralytics/pull/26242) from [@cainiao33](https://github.com/cainiao33):

- Refreshes remote manifests inside the existing conversion lock to prevent stale datasets from being reused.
- Isolates downloads in private temporary directories, avoiding collisions between similarly named manifests.
- Reuses cached datasets when content is unchanged, including when signed URLs rotate.
- Creates separate dataset directories for changed manifests, protecting files used by active training jobs.
- Improves predictable file handling by removing NDJSON-specific deletion behavior from `check_file`.
- Covers detection, classification, depth, local sources, concurrent downloads, interrupted conversions, and URL basename collisions.

These changes mean more trustworthy dataset updates with less unnecessary network and disk usage. ✅

## ⚡ Faster INT8 TensorRT Exports

INT8 deployment receives significant QAT and PTQ improvements through [PR #26171](https://github.com/ultralytics/ultralytics/pull/26171) by [@Y-T-G](https://github.com/Y-T-G):

- Quantizes more of the model head during QAT.
- Keeps accuracy-sensitive output layers and DFL operations in floating point.
- Fuses BatchNorm layers during export, prediction, and validation to reduce runtime overhead.
- Adjusts quantization ranges after BatchNorm fusion so effective INT8 values remain stable.
- Uses FP16 where appropriate for sensitive PTQ head operations.
- Refines precision handling across newer and older TensorRT versions.

The result is faster, more efficient TensorRT engines without unnecessarily quantizing accuracy-sensitive operations. 🎯

## 🧪 Testing Improvements

Cross-platform model validation is more robust following [PR #26217](https://github.com/ultralytics/ultralytics/pull/26217) from [@glenn-jocher](https://github.com/glenn-jocher).

Restricted-load testing now uses tolerant numerical comparison instead of requiring bit-for-bit identical outputs across every hardware backend. This reduces harmless false failures—particularly on embedded and Jetson environments—while continuing to validate model weights, criteria, and fused layers.

## 🛠 Maintenance and Documentation

This release also includes several infrastructure and documentation updates:

- [PR #26229](https://github.com/ultralytics/ultralytics/pull/26229) by [@UltralyticsAssistant](https://github.com/UltralyticsAssistant) updates the self-hosted GitHub Actions cleanup runner from `v1.4.39` to `v1.4.40`.
- [PR #26235](https://github.com/ultralytics/ultralytics/pull/26235) by [@RizwanMunawar](https://github.com/RizwanMunawar) refreshes the embedded video in the Security Alarm System guide.
- Export documentation now describes the more precise QAT model-head behavior.

## 📦 Upgrade Today

Install or upgrade to v8.4.156 with:

```bash
pip install -U ultralytics

```

There are no major user-facing API changes, so existing workflows should continue working while benefiting from improved dataset conversion, TensorRT deployment, and test stability.

Explore the complete details on the [Ultralytics v8.4.156 release page](https://github.com/ultralytics/ultralytics/releases/tag/v8.4.156), or review every update in the [full v8.4.155 to v8.4.156 changelog](https://github.com/ultralytics/ultralytics/compare/v8.4.155...v8.4.156).

Give the new release a try, and let the Ultralytics team and YOLO community know how it performs in your training and deployment workflows! 🚀