# New Release: Ultralytics v8.4.90 **URL:** \ **Category:** Discussion\ **Tags:** releases, announcements, ultralytics-official\ **Created:** [July 7, 2026, 1:44pm UTC](https://community.ultralytics.com/t/new-release-ultralytics-v8-4-90/2102 "2026-07-07T13:44:20Z")\ **Posts on this page:** 1\ **Page:** 1

**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 7, 2026, 1:44pm UTC](https://community.ultralytics.com/t/new-release-ultralytics-v8-4-90/2102/1 "2026-07-07T13:44:20Z")

## 🚀 Ultralytics v8.4.90 is here! Ultralytics `v8.4.90` is now available, bringing a major new **YOLO Architecture Explained** guide, improved tracking reliability, stronger segmentation edge-case handling, updated Docker GPU guidance, and cleaner contributor workflows 🎉 This release helps users better understand the evolution from YOLOv3 through YOLO26, improves real-world tracking stability, and makes segmentation and container workflows more robust. Read the full release on GitHub in the [Ultralytics v8.4.90 release notes](https://github.com/ultralytics/ultralytics/releases/tag/v8.4.90). 📦 * * * ## 🌟 Highlights ### 📚 New YOLO Architecture Explained guide This release adds a detailed new guide explaining the evolution of Ultralytics YOLO architectures from **YOLOv3 → YOLOv5 → YOLOv8 → YOLO11 → YOLO26**. The guide covers key architecture components across the **backbone, neck, and detection head** , including: - `Bottleneck` - `C3` - `C2f` - `C3k2` - `SPPF` - `C2PSA` - `DFL` - Anchor-free detection - YOLO26’s NMS-free and DFL-free design It also includes stage-level Mermaid diagrams, model inspection details, and links to relevant YAML configs and module definitions. Contributed by @raimbekovm in [PR #24970](https://github.com/ultralytics/ultralytics/pull/24970) 🙌 * * * ## 🎯 Tracking Improvements ### More reliable ByteTrack and FastTrack recovery `BYTETracker` and `FastTracker` now better preserve track IDs when detections briefly drop in confidence. This fixes second-stage association when `fuse_score=True`, ensuring low-confidence detections can correctly recover existing tracks using IoU-only matching, matching ByteTrack’s intended behavior. Contributed by @JESUSROYETH in [PR #25034](https://github.com/ultralytics/ultralytics/pull/25034) ✅ * * * ## 🧩 Segmentation Fixes ### Empty mask inputs are now handled safely Segmentation utilities now correctly support valid empty inputs with zero detections. Updated utilities include: - `process_mask` - `process_mask_native` - `scale_masks` These functions now return correctly shaped empty tensors instead of crashing, improving robustness for exported models and frame-by-frame inference workflows. Contributed by @JESUSROYETH in [PR #25032](https://github.com/ultralytics/ultralytics/pull/25032) 🛠 * * * ## 🐳 Docker and GPU Updates ### Modern CDI GPU device requests Docker GPU examples have been updated from legacy flags such as `--runtime=nvidia --gpus all` to modern CDI-style device requests like: ```bash --device nvidia.com/gpu=all ``` This update improves guidance across Dockerfiles, quickstarts, Triton docs, DGX Spark docs, and YOLOv5 Docker documentation. The docs now also clarify that CDI requires Docker `>= 28.2.0` and NVIDIA Container Toolkit `>= 1.18`, while still noting legacy flags for older systems. Contributed by @glenn-jocher in [PR #25040](https://github.com/ultralytics/ultralytics/pull/25040) 🐋 * * * ## 🤖 Contributor Workflow Updates ### New AI-agent contributor guidance This release adds `AGENTS.md` with repository overview, engineering principles, development commands, PR workflow expectations, and architecture notes. A `CLAUDE.md` symlink was also added for Claude Code compatibility, helping AI coding tools and contributors work more consistently in the Ultralytics repository. Contributed by @glenn-jocher in [PR #25035](https://github.com/ultralytics/ultralytics/pull/25035) and [PR #25036](https://github.com/ultralytics/ultralytics/pull/25036) 🤝 * * * ## 🧹 User Experience Improvements ### Cleaner safe-load behavior An unnecessary warning was removed when restricted model loading is unavailable on older PyTorch versions. This reduces log noise without changing model loading behavior. Contributed by @glenn-jocher in [PR #25033](https://github.com/ultralytics/ultralytics/pull/25033) 🔇 * * * ## 🧪 CI Stability ### NumPy pin for legacy PyTorch slow tests NumPy is now pinned to `<2` for the PyTorch `2.3.0` / torchvision `0.18.0` slow-test shard to avoid a known `ColorJitter` hue overflow issue. Contributed by @onuralpszr in [PR #25037](https://github.com/ultralytics/ultralytics/pull/25037) 🧪 * * * ## 🔗 Documentation Cleanup ### Updated solution links Renamed Ultralytics solutions URLs were updated from older `ai-in-*` paths to newer `computer-vision-in-*` paths. Contributed by @miles-deans-ultralytics in [PR #25039](https://github.com/ultralytics/ultralytics/pull/25039) 📘 * * * ## 📋 Full PR List - 🔇 Silence safe load fallback warning by @glenn-jocher in [PR #25033](https://github.com/ultralytics/ultralytics/pull/25033) - 🤖 Add `AGENTS.md` agent guidance with `CLAUDE.md` symlink by @glenn-jocher in [PR #25035](https://github.com/ultralytics/ultralytics/pull/25035) - 📚 Lead `AGENTS.md` with repository overview by @glenn-jocher in [PR #25036](https://github.com/ultralytics/ultralytics/pull/25036) - 🎯 Fix ByteTrack second association ignoring low-confidence detections with `fuse_score=True` by @JESUSROYETH in [PR #25034](https://github.com/ultralytics/ultralytics/pull/25034) - 🧩 Fix `process_mask`, `process_mask_native`, and `scale_masks` on empty zero-detection inputs by @JESUSROYETH in [PR #25032](https://github.com/ultralytics/ultralytics/pull/25032) - 🧪 Pin NumPy `<2` for torch `2.3.0` / torchvision `0.18.0` SlowTests shard by @onuralpszr in [PR #25037](https://github.com/ultralytics/ultralytics/pull/25037) - 🔗 Update links to renamed solution pages by @miles-deans-ultralytics in [PR #25039](https://github.com/ultralytics/ultralytics/pull/25039) - 🐳 Replace legacy `--gpus` examples with CDI device requests across docs and Dockerfiles by @glenn-jocher in [PR #25040](https://github.com/ultralytics/ultralytics/pull/25040) - 📚 Add YOLO architecture explained guide by @raimbekovm in [PR #24970](https://github.com/ultralytics/ultralytics/pull/24970) * * * ## ✅ Try it now Upgrade with: ```bash pip install -U ultralytics ``` Then try your favorite workflow: ```bash yolo predict model=yolo11n.pt source=image.jpg ``` * * * ## 🙌 Thanks to the community Huge thanks to all contributors and the YOLO community for testing, reporting issues, improving documentation, and helping make Ultralytics better with every release. You can review every change in the [full v8.4.89 to v8.4.90 changelog](https://github.com/ultralytics/ultralytics/compare/v8.4.89...v8.4.90). Please upgrade, try the new release, and share feedback in Discussions or Issues 🚀