# New Release: Ultralytics v8.4.32

**URL:** <https://community.ultralytics.com/t/new-release-ultralytics-v8-4-32/1907>\
**Category:** Discussion\
**Tags:** releases, announcements, ultralytics-official\
**Created:** [March 31, 2026, 1:34pm UTC](https://community.ultralytics.com/t/new-release-ultralytics-v8-4-32/1907 "2026-03-31T13:34:05Z")\
**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:** [March 31, 2026, 1:34pm UTC](https://community.ultralytics.com/t/new-release-ultralytics-v8-4-32/1907/1 "2026-03-31T13:34:05Z")

</div>

## Ultralytics v8.4.32 is out 🎉

**Quick summary:** `v8.4.32` is a deployment-focused release centered on a major **Axelera AI export expansion** 🚀, with cleaner export architecture, broader task support across Ultralytics YOLO models, new end-to-end examples, and several helpful documentation improvements for both the repo and the [Ultralytics Platform](https://platform.ultralytics.com).

If you deploy on edge hardware, especially Axelera devices, this is a great release to try. If you use Platform for dataset workflows, this update also makes a few important behaviors and limits much clearer ✅

* * *

## 🌟 Highlights

### Axelera export expansion and refactor

The biggest change in `v8.4.32` comes from [PR #23844 by @lakshanthad](https://github.com/ultralytics/ultralytics/pull/23844), which significantly improves Axelera export and deployment workflows.

Key upgrades include:

- Moved Axelera export logic into a dedicated utility module: `ultralytics/utils/export/axelera.py`
- Introduced reusable `torch2axelera` helper for a cleaner export pipeline
- Expanded export support beyond detection-only messaging to better cover multiple YOLO task workflows across **YOLOv8, YOLO11, and YOLO26**
- Added task-aware calibration defaults via `TASK2CALIBRATIONDATA`
- Clarified export requirements and limitations, including:
  - Linux-only support
  - no ARM64 Docker support
  - Torch `2.8+` requirement

This makes the Axelera path easier to maintain, easier to understand, and more practical for real deployment scenarios 🧠⚙

### Better Axelera runtime support

This release also updates Axelera backend/runtime handling with newer package paths and more direct `.axm` pipeline loading and optimization, helping smooth the path from export to inference 🔌

### New deployment examples

`v8.4.32` adds practical Python deployment examples for:

- **YOLO26 pose + tracking**
- **YOLO11 segmentation**

These examples are especially useful because they demonstrate full inference pipelines on Axelera hardware without requiring Ultralytics at inference runtime 📁🎯

* * *

## 📚 Documentation improvements

A big part of this release is improved documentation across both the Ultralytics repo and the [Ultralytics Platform docs](https://docs.ultralytics.com/platform/).

### Axelera docs updates

The Axelera integration docs were expanded with:

- supported tasks tables
- Python version support for `3.10`, `3.11`, and `3.12`
- clearer installation steps
- known limitations
- benchmark tables
- new reference docs for the Axelera export utility

### Platform docs clarifications

This release also improves Platform documentation to reduce confusion in day-to-day workflows:

- multi-task annotation persistence is now clearly documented, via [PR #24044 by @t-hakobyan](https://github.com/ultralytics/ultralytics/pull/24044) ✅
- dataset upload limits were clarified for Free, Pro, and Enterprise plans in [PR #24057 by @glenn-jocher](https://github.com/ultralytics/ultralytics/pull/24057)
- `.tar.gz` and `.tgz` dataset upload support was documented in [PR #24058 by @glenn-jocher](https://github.com/ultralytics/ultralytics/pull/24058)

### Docs UI polish

A few nice usability improvements landed too:

- updated docs banner in [PR #24009 by @raimbekovm](https://github.com/ultralytics/ultralytics/pull/24009)
- inline code overlap fix in [PR #24054 by @Y-T-G](https://github.com/ultralytics/ultralytics/pull/24054)
- chat widget update in [PR #24053 by @glenn-jocher](https://github.com/ultralytics/ultralytics/pull/24053)
- added docs video in [PR #24055 by @RizwanMunawar](https://github.com/ultralytics/ultralytics/pull/24055)

* * *

## 🔧 Why this release matters

### For developers

- Cleaner export internals mean easier maintenance and faster iteration
- Reusable Axelera utilities should reduce regression risk
- Better calibration defaults mean less manual export setup

### For edge deployment users

- Broader support across **YOLOv8, YOLO11, and YOLO26** improves real-world deployment flexibility
- New examples help bridge the gap from trained model to production-style inference
- More explicit limitations make setup more predictable

### For Platform users

- Clearer dataset upload format and size documentation reduces workflow friction
- Better annotation behavior documentation helps avoid accidental assumptions
- Small UI fixes improve the docs experience overall

* * *

## 🧾 What changed

- [PR #24053 by @glenn-jocher](https://github.com/ultralytics/ultralytics/pull/24053) — Update `chat.js` to `v0.2.8`
- [PR #24054 by @Y-T-G](https://github.com/ultralytics/ultralytics/pull/24054) — Fix overlapping text with inline code in docs
- [PR #24055 by @RizwanMunawar](https://github.com/ultralytics/ultralytics/pull/24055) — Add video to docs
- [PR #24044 by @t-hakobyan](https://github.com/ultralytics/ultralytics/pull/24044) — Add multi-task annotation storage documentation
- [PR #24057 by @glenn-jocher](https://github.com/ultralytics/ultralytics/pull/24057) — Clarify Pro and Enterprise dataset upload limits
- [PR #24058 by @glenn-jocher](https://github.com/ultralytics/ultralytics/pull/24058) — Add `.tar.gz` / `.tgz` docs updates
- [PR #24009 by @raimbekovm](https://github.com/ultralytics/ultralytics/pull/24009) — Update docs banner
- [PR #23844 by @lakshanthad](https://github.com/ultralytics/ultralytics/pull/23844) — Expand Axelera exportable models and tasks

For the full diff, check the [full changelog from `v8.4.31` to `v8.4.32`](https://github.com/ultralytics/ultralytics/compare/v8.4.31...v8.4.32), and you can browse the complete release on the [Ultralytics `v8.4.32` release page](https://github.com/ultralytics/ultralytics/releases/tag/v8.4.32).

* * *

## 🙌 Try it out

We’d love for the community to test `v8.4.32`, especially if you’re working with Axelera deployments, multi-task annotation workflows, or the latest Ultralytics YOLO models like [YOLO26](https://platform.ultralytics.com/ultralytics/yolo26).

If you give it a spin, please share your feedback, results, and any edge cases you run into. Your input helps make each release better for everyone 💙