# New Release: Ultralytics v8.4.133 **URL:** \ **Category:** Discussion\ **Tags:** ultralytics-official, releases, announcements\ **Created:** [August 29, 2026, 1:07pm UTC](https://community.ultralytics.com/t/new-release-ultralytics-v8-4-133/2193 "2026-08-29T13:07:45Z")\ **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:** [August 29, 2026, 1:07pm UTC](https://community.ultralytics.com/t/new-release-ultralytics-v8-4-133/2193/1 "2026-08-29T13:07:45Z")
# 🚀 Ultralytics v8.4.133: Faster Inference, Smarter Tuning, and Richer Metrics Ultralytics v8.4.133 is now available! This release delivers **better hyperparameter tuning convergence** , **faster inference preprocessing** , **automatic CPU optimizations** , **more reliable INT8 calibration** , and **size-specific detection metrics**. Edge-device installation and Weights & Biases artifact management are also simpler. 🎯 Review the official [Ultralytics v8.4.133 release](https://github.com/ultralytics/ultralytics/releases/tag/v8.4.133) for the complete release details. ## 🌟 New Features ### Smarter hyperparameter tuning [PR #25984](https://github.com/ultralytics/ultralytics/pull/25984) from [@glenn-jocher](https://github.com/glenn-jocher) significantly improves tuning convergence: - Selects complete, high-performing configurations using fitness weighting. - Preserves useful relationships between hyperparameters. - Mutates parameters in normalized search-space coordinates, allowing zero-valued parameters such as `degrees` and `shear` to evolve effectively. - Gradually reduces mutation size when improvements slow down. - Prevents duplicate candidates in small or discrete search spaces. - Uses Optuna multivariate TPE with parallel-aware suggestions as the Ray Tune default. These changes help searches explore broadly before refining the most promising configurations. 🎯 ### Size-specific mAP for custom datasets [PR #25981](https://github.com/ultralytics/ultralytics/pull/25981) from [@fcakyon](https://github.com/fcakyon) adds small-, medium-, and large-object mAP reporting for custom detection datasets when `save_json=True`. Temporary COCO-format annotations are generated internally while preserving native metrics and prediction files. The feature works during training validation, final-model validation, and standalone validation. 📈 ## ⚡ Performance Improvements ### Faster predictor preprocessing [PR #25982](https://github.com/ultralytics/ultralytics/pull/25982) from [@jahsef](https://github.com/jahsef) moves image channel reordering and tensor-contiguity operations from CPU-side NumPy processing to the inference device. This preserves output values while reducing unnecessary CPU copies. Reported RTX 5080 benchmarks show approximately **2.2–3.1× faster preprocessing** , with additional gains observed on CPU. ### Automatic channels-last CPU inference [PR #25983](https://github.com/ultralytics/ultralytics/pull/25983) from [@JESUSROYETH](https://github.com/JESUSROYETH) automatically enables channels-last memory layout for native PyTorch inference and standalone validation on supported x86 Linux and Windows CPUs with oneDNN. Training defaults and unsupported platforms remain unchanged, while explicit `channels_last=True` continues to support compatible CPU and CUDA workflows. Saved models are restored to a safe contiguous format, and stale EMA data is cleared for improved compatibility. ## 🛠 Bug Fixes and Reliability ### Correct INT8 calibration fractions [PR #25978](https://github.com/ultralytics/ultralytics/pull/25978) from [@JESUSROYETH](https://github.com/JESUSROYETH) fixes `fraction` handling for classification and detection INT8 export calibration. Scalar fractions now apply directly to the selected calibration split, while list-based fractions retain train, validation, and test behavior. This prevents unexpectedly calibrating against an entire dataset when only a subset was requested. ### Improved W&B artifact control Initial W&B artifact controls arrived through [PR #25979](https://github.com/ultralytics/ultralytics/pull/25979) from [@fcakyon](https://github.com/fcakyon), followed by integration with the standard training `save` argument in [PR #25985](https://github.com/ultralytics/ultralytics/pull/25985) from [@glenn-jocher](https://github.com/glenn-jocher). Using `save=False` now skips uploading the best checkpoint while retaining metrics and plots. The default behavior remains unchanged with `save=True`. ## 🍓 Simpler Edge-Device Setup [PR #25977](https://github.com/ultralytics/ultralytics/pull/25977) from [@Y-T-G](https://github.com/Y-T-G) updates Raspberry Pi, Jetson, DGX Spark, DeepStream, and related installation guides to use the base `ultralytics` package instead of the larger `[export]` extra. Export dependencies are installed automatically when needed, helping reduce installation size and avoid dependency conflicts on edge devices. ## 📦 Upgrade Today Install or upgrade to v8.4.133 with: ```bash pip install -U ultralytics ``` You can inspect every update in the [full v8.4.132 to v8.4.133 changelog](https://github.com/ultralytics/ultralytics/compare/v8.4.132...v8.4.133). Give the new release a try and share your benchmarks, feedback, and any issues you encounter. Thanks to every contributor and the wider YOLO community for continuing to improve Ultralytics YOLO! 🙌