# ultralytics v8.4.141 — v8.4.141 - Update Axelera SDK to 1.8.0 and support batched inference (#26065) - Product: ultralytics (https://whatsnew.fyi/product/ultralytics) - Vendor: ultralytics - Date: 2026-09-05 - Version: v8.4.141 - Original notes: https://github.com/ultralytics/ultralytics/releases/tag/v8.4.141 - Permalink: https://whatsnew.fyi/product/ultralytics/releases/v8.4.141 What's New is an index, not a publisher: every entry below links to the vendor's own release notes, which are the authoritative source. Entries are labelled where they are hand-curated sample data, pre-releases, or drawn from a secondary source such as a developer blog. Reuse: the summaries, labels and curation here are © What's New. Quote freely with attribution and a link back; wholesale republication of the corpus is not permitted — terms: https://whatsnew.fyi/terms. The vendors' own release notes remain their publishers'. --- - **changed** — Upgrade Axelera integration to Voyager SDK 1.8.0 with matching axelera-devkit and axelera-rt packages - **changed** — Move Axelera export environments to Python 3.13 and support wider compatible PyTorch range - **changed** — Remove NumPy version ceiling and improve SDK version checks before compiler loading in Axelera export - **changed** — Ensure Axelera export sets correct SDK environment tools on PATH and safely restores environment variables afterward - **added** — Support batched Axelera inference with batch>1 routed through the Voyager scheduler - **changed** — Return Axelera inference outputs in original input order for both single- and multi-output models - **fixed** — Restore SPPF cv1 activation for pre-YOLO26 models to preserve released model graphs and outputs - **changed** — Move OpenVINO and NNCF dependencies from export-base to dedicated export-openvino extra - **changed** — Update Conda CI to use only conda-forge with strict channel priority and remove inherited default channels - **changed** — Set Conda CI installations to noninteractive with 20-minute timeout to prevent stalled dependency solves ##### 🌟 Summary **Ultralytics 8.4.141 updates Axelera support to Voyager SDK 1.8.0, adds batched inference, and improves model compatibility, dependency management, and CI reliability.** 🚀 ##### 📊 Key Changes - **Axelera integration upgraded to Voyager SDK 1.8.0** 🔧 - Export and inference now use matching `axelera-devkit` and `axelera-rt` 1.8.0 packages. - Axelera export environments move to **Python 3.13** and support a wider compatible PyTorch range. - Removed the previous NumPy version ceiling and improved SDK version checks before compiler loading. - Export now ensures the correct SDK environment tools are available on `PATH` and safely restores environment variables afterward. - **Batched Axelera inference is now supported** 📦 - Predictions with `batch>1` are routed through the Voyager scheduler. - Outputs are returned in the original input order for both single- and multi-output models. - Models are still compiled for a single image, so batching improves workflow compatibility but does not necessarily increase end-to-end speed on one device. - **Axelera deployment requirements are documented more clearly** 📚 - Voyager SDK 1.8.0 requires the **Metis kernel driver 1.6.2 or newer**. - Models exported with an older SDK must be re-exported because SDK 1.8 uses a newer compiled model format. - YOLO26 semantic segmentation is documented as supported, while YOLO26 instance segmentation remains unavailable through the Ultralytics export command. - **Fixed legacy SPPF model reconstruction** 🛠️ - Pre-YOLO26 YAML configurations once risked rebuilding `SPPF` layers with the wrong activation behavior. - Legacy models now restore their original activation settings, preserving released model graphs and outputs. - Regression coverage now checks multiple YOLO configurations, including YOLO8, YOLO10, YOLO11, and YOLO26. - **OpenVINO dependencies are now opt-in** 📦 - OpenVINO and NNCF moved from `export-base` to a dedicated `export-openvino` extra. - The aggregate `export` extra still includes OpenVINO support. - This reduces unnecessary installations for users who only need the common export stack. - **Conda CI dependency resolution improved** ⚡ - CI now uses only `conda-forge` with strict channel priority and removes inherited default channels. - Installation is noninteractive and has a 20-minute timeout, preventing stalled dependency solves from consuming the full job. ##### 🎯 Purpose & Impact - **Axelera users** can use the latest SDK, run inference on image batches, and benefit from more reliable automatic dependency handling. Existing Axelera models may need to be re-exported after upgrading. ⚠️ - **Deployment compatibility** is improved, but users must keep the Metis driver aligned with Voyager SDK 1.8.0. - **Legacy Ultralytics models** are safer to rebuild from YAML without silently changing SPPF behavior. - **General installations** become lighter when OpenVINO is not required, while OpenVINO export remains available through its dedicated extra or the full export installation. - **Contributors and maintainers** benefit from faster, more predictable Conda CI failures and clearer environment setup. - The release increments the package version to **8.4.141**, enabling downstream Ultralytics Platform updates to require the corrected Axelera exporter. ##### What's Changed * Restore SPPF cv1 activation for pre-YOLO26 models by @Erickrk in https://github.com/ultralytics/ultralytics/pull/26040 * Fix Conda CI dependency resolution and install timeout by @glenn-jocher in https://github.com/ultralytics/ultralytics/pull/26064 * Move OpenVINO dependencies out of the base install extra by @Gornoka in https://github.com/ultralytics/ultralytics/pull/26038 * Update Axelera SDK to 1.8.0 and support batched inference by @glenn-jocher in https://github.com/ultralytics/ultralytics/pull/26065 ##### New Contributors * @Erickrk made their first contribution in https://github.com/ultralytics/ultralyt _[Truncated at 4000 characters — full notes: https://github.com/ultralytics/ultralytics/releases/tag/v8.4.141]_