# New Release: Ultralytics v8.4.100

**URL:** <https://community.ultralytics.com/t/new-release-ultralytics-v8-4-100/2129>\
**Category:** Discussion\
**Tags:** ultralytics-official, releases, announcements\
**Created:** [July 18, 2026, 1:31pm UTC](https://community.ultralytics.com/t/new-release-ultralytics-v8-4-100/2129 "2026-07-18T13:31:03Z")\
**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 18, 2026, 1:31pm UTC](https://community.ultralytics.com/t/new-release-ultralytics-v8-4-100/2129/1 "2026-07-18T13:31:03Z")

</div>

# 🚀 Ultralytics v8.4.100: Hailo Segmentation, Stronger Exports, and Better Reliability

Ultralytics **v8.4.100** expands edge deployment with **Hailo instance segmentation support for YOLOv8 and YOLO11** , clearer INT8 and TensorRT guidance, broader fuzz testing, improved Platform workers, cleaner training errors, and more reliable Axelera exports.

Explore the [v8.4.100 release](https://github.com/ultralytics/ultralytics/releases/tag/v8.4.100) for the complete release details.

## 🌟 New Features

### 🟢 Hailo Instance Segmentation

[PR #25259](https://github.com/ultralytics/ultralytics/pull/25259) by [@JESUSROYETH](https://github.com/JESUSROYETH) adds Hailo HEF export and inference support for **YOLOv8-seg and YOLO11-seg**.

- Supports Hailo-8, Hailo-8L, Hailo-10, and Hailo-15 accelerators.
- Exports raw segmentation tensors for Ultralytics-side decoding, bounding-box processing, NMS, and mask generation.
- Preserves the standard Ultralytics prediction format and existing mask workflows.
- Avoids Hailo on-chip NMS configuration for segmentation models.
- Clearly rejects YOLO26 segmentation because Hailo-8 and Hailo-8L cannot allocate its attention-based architecture.

YOLO26 remains the latest stable and recommended Ultralytics model for new projects, while YOLO11 continues to be fully supported.

## 📚 Deployment Improvements

### Better Hailo INT8 Guidance

[PR #25260](https://github.com/ultralytics/ultralytics/pull/25260) by [@JESUSROYETH](https://github.com/JESUSROYETH) adds practical INT8 accuracy guidance for YOLOv8, YOLO11, and YOLO26 on Hailo-8L.

The updated guidance explains:

- Why calibration data should closely match the production domain.
- Why YOLO26 confidence scores may be approximately `0.05` lower on Hailo devices.
- Why attention layers can be more sensitive to INT8 quantization on Hailo-8 and Hailo-8L.

### Clearer TensorRT Compatibility Warnings

[PR #25263](https://github.com/ultralytics/ultralytics/pull/25263) by [@lakshanthad](https://github.com/lakshanthad) improves Platform export documentation with clearer TensorRT compatibility requirements.

Downloaded TensorRT engines must match the target GPU family, TensorRT version, CUDA runtime, and build environment. When environments differ, users are now directed to export the engine locally on the deployment device.

## 🧪 Testing and Reliability

### Expanded Fuzz Testing

[PR #25262](https://github.com/ultralytics/ultralytics/pull/25262) by [@glenn-jocher](https://github.com/glenn-jocher) broadens fuzz coverage across:

- Tracking and cached video.
- Malformed media and Unicode paths.
- Additional model families.
- CoreML on macOS.
- Shell-safe reproducer commands.

Duplicate commands are now skipped, and the fuzzing budget increases from 285 to 300 minutes per run for more effective exploration.

### More Reliable Axelera Exports

[PR #25267](https://github.com/ultralytics/ultralytics/pull/25267) by [@glenn-jocher](https://github.com/glenn-jocher) fixes compatibility issues with Axelera Devkit 1.7.0 by pinning `omnimalloc==0.5.0`.

Runtime checks now validate the same allocator version before export, reducing environment-related failures.

## 🛠 Training and Platform Improvements

### Cleaner Errors for Invalid Small Training Configurations

[PR #25264](https://github.com/ultralytics/ultralytics/pull/25264) by [@glenn-jocher](https://github.com/glenn-jocher) replaces a confusing low-level PyTorch BatchNorm failure with an actionable error.

When `batch=1` is combined with an image size that is too small, training now fails early and recommends increasing the batch size or image size.

### Improved Managed-Worker Integration

[PR #25266](https://github.com/ultralytics/ultralytics/pull/25266) by [@glenn-jocher](https://github.com/glenn-jocher) improves managed-worker integration by:

- Reusing existing Platform training callbacks.
- Supporting configurable API endpoints through `PLATFORM_API_URL`.
- Respecting the current `SETTINGS["runs_dir"]` value when creating training output paths.

For a streamlined workflow covering dataset annotation, training, deployment, and monitoring, try the [Ultralytics Platform](https://platform.ultralytics.com).

## 📦 Get Started

Upgrade to the latest release:

```bash
pip install -U ultralytics

```

Review every change in the [v8.4.99 to v8.4.100 comparison](https://github.com/ultralytics/ultralytics/compare/v8.4.99...v8.4.100), then try the new Hailo segmentation workflow and deployment improvements.

Thanks to the YOLO community and all contributors who helped make this release possible. Please share your results, questions, and feedback below! 🙌