# New Release: Ultralytics v8.4.173

**URL:** <https://community.ultralytics.com/t/new-release-ultralytics-v8-4-173/2250>\
**Category:** Discussion\
**Tags:** announcements, ultralytics-official, releases\
**Created:** [October 5, 2026, 1:16pm UTC](https://community.ultralytics.com/t/new-release-ultralytics-v8-4-173/2250 "2026-10-05T13:16:24Z")\
**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:** [October 5, 2026, 1:16pm UTC](https://community.ultralytics.com/t/new-release-ultralytics-v8-4-173/2250/1 "2026-10-05T13:16:24Z")

</div>

# 🚀 Ultralytics v8.4.173: Native AMD Xilinx Export and Leaner Docker Images

**Ultralytics YOLO v8.4.173 adds native export for AMD Versal AI Edge Series Gen 2 NPUs** , bringing a new deployment path to supported AMD edge hardware. This release also reduces Docker image sizes, expands PyTorch dependency support, and improves documentation.

## 🆕 New Features: AMD Xilinx Export

The [native AMD Xilinx export in PR #26519](https://github.com/ultralytics/ultralytics/pull/26519), contributed by [@glenn-jocher](https://github.com/glenn-jocher), introduces:

- **A new `xilinx` export format:** Export through AMD Quark to a quantized ONNX model and Vitis AI configuration. Accepted aliases include `vitis`, `vitisai`, and `versal`.
- **Mixed-precision deployment:** Most of the model uses INT8 quantization, while the head remains in floating point for the Vitis AI compiler to run in BF16.
- **Validation before deployment:** Validate the exported model on a CPU, then use AMD’s Vitis AI tools to compile it into a `.rai` model for the NPU.
- **Targeted hardware support:** Native export supports **Versal AI Edge Gen 2 devices, including the VEK385**.

> 📌 This is **not a universal Xilinx export**. Older Zynq, Kria, and first-generation Versal devices still require separate, device-specific AMD workflows.

The [AMD Xilinx deployment guide added in PR #26517](https://github.com/ultralytics/ultralytics/pull/26517), also contributed by [@glenn-jocher](https://github.com/glenn-jocher), covers export, deployment, hardware compatibility, and which operations may run on the NPU versus the CPU.

INT8 quantization can reduce deployment footprint, while a BF16 head helps preserve accuracy. Actual accuracy and speed depend on calibration data, compilation, and the target device.

## 🐳 Improvements: Smaller Images and Broader Dependency Support

- **Leaner Docker images:** The [Docker cleanup in PR #26514](https://github.com/ultralytics/ultralytics/pull/26514) by [@glenn-jocher](https://github.com/glenn-jocher) removes unused OpenCV GUI libraries, `gnupg`, and other unnecessary system packages. Reported root-filesystem savings range from **about 184 MB to 305 MB** , depending on the image. Users who need GUI display can install the GUI OpenCV build explicitly.
- **Broader PyTorch support:** The [dependency update in PR #26463](https://github.com/ultralytics/ultralytics/pull/26463) by [@dependabot[bot]](https://docs.github.com/en/code-security/how-tos/secure-your-supply-chain/secure-your-dependencies/configure-security-updates) expands the updated `torch` requirement from `>=2.12.0,<2.13.0` to `>=2.12.0,<2.15.0`.

## 🔧 Documentation Fixes

Three updates from [@glenn-jocher](https://github.com/glenn-jocher) improve documentation usability:

- The [Markdown fixes in PR #26513](https://github.com/ultralytics/ultralytics/pull/26513) correct raw Markdown rendering in the Vertex AI guide and metric docstrings.
- The [language-link fix in PR #26515](https://github.com/ultralytics/ultralytics/pull/26515) keeps documentation home language links untranslated.
- The [link corrections in PR #26516](https://github.com/ultralytics/ultralytics/pull/26516) repair the ETH3D link and Triton localhost reference.

## 💬 Try It and Share Your Feedback

Install this release with:

```bash
pip install --upgrade ultralytics==8.4.173

```

Explore the [v8.4.173 release notes](https://github.com/ultralytics/ultralytics/releases/tag/v8.4.173) for release details, or review the [full changelog](https://github.com/ultralytics/ultralytics/compare/v8.4.172...v8.4.173) to see every change.

Testing on supported AMD hardware or using the slimmer Docker images? Share your results, questions, and feedback below. Thanks to the Ultralytics team and YOLO community for helping improve every release! 🎉