Announcing Ultralytics YOLO v8.2.79 Release!
 Summary
We are thrilled to announce the release of Ultralytics YOLO v8.2.79! This update brings significant improvements in documentation workflows, a refined deployment process, and enhanced compatibility for inference tasks. Dive into the details below to see what’s new and improved.
 Key Changes
Documentation Workflow Overhaul
- What’s New: The documentation workflow (
docs.yml) has been established as a separate process. - Impact: This change streamlines documentation updates, ensuring users have access to the latest insights and instructions without any hiccups.
 - PR: Split Docs action into separate workflow by @glenn-jocher
 
Publishing Process Updates
- What’s New: Adjustments to the publishing workflow ensure cleaner and more efficient version checking and deployment, focusing now solely on PyPI without doc deployments.
 - Impact: This fine-tuning focuses development efforts on core functionalities and ensures versions are correctly managed and published.
 - PR: Simplify publish action by @glenn-jocher
 
Inference Resolution Change
- What’s New: The inference example now uses a resolution of 640x640 instead of 640x480.
 - Impact: This update enhances detection accuracy, making the solution better suited for high-resolution object detection tasks.
 - PR: Fix YOLOv8 C++ Example model input size by @AD-lite24
 
Enhanced Compatibility
- What’s New: Updates in the model’s post-processing provide better compatibility with Apple’s MPS and CoreML.
 - Impact: Ensures that Ultralytics software runs smoothly on macOS, expanding the capability across different hardware setups and enhancing user experience.
 - PR: YOLOv10 CoreML and MPS training “gather” op error fix by @Oil3
 
 Purpose & Impact
- Documentation Clarity and Efficiency: Separating doc updates into a dedicated workflow allows for more organized and error-free documentation updates.
 - Streamlined Release Management: Focuses the development efforts on core functionalities and ensures versions are correctly managed and published.
 - Improved Detection Performance: Enhances detection accuracy, making the solution better suited for high-resolution object detection tasks.
 - Broadened Compatibility: Ensures smooth operation on macOS, enhancing user experience across different hardware setups.
 
These enhancements strive to make Ultralytics’ tools more robust, user-friendly, and functionally versatile for all users, from developers to dataset trainers. ![]()
What’s Changed
- Split Docs action into separate workflow by @glenn-jocher
 - Add https://youtu.be/28JV4rbzklM to docs by @RizwanMunawar
 - Fix YOLOv8 C++ Example model input size by @AD-lite24
 - Skip Docs push if no changes by @glenn-jocher
 - Simplify publish action by @glenn-jocher
 - Bump contributor-assistant/github-action from 2.4.0 to 2.5.1 in /.github/workflows by @dependabot
 ultralytics 8.2.79YOLOv10 CoreML and MPS training “gather” op error fix by @Oil3
New Contributors
- @AD-lite24 made their first contribution in Fix YOLOv8 C++ Example model input size
 - @Oil3 made their first contribution in YOLOv10 CoreML and MPS training “gather” op error fix
 
Full Changelog: v8.2.78…v8.2.79
Release URL: Ultralytics YOLO v8.2.79
We encourage you to try out the new release and share your feedback. Your insights are invaluable in helping us improve and evolve. Happy coding! ![]()