Ultralytics v8.4.81 is out 
Quick summary: Ultralytics YOLO v8.4.81 is a polish-and-reliability release focused on FastSAM stability, safer and clearer export precision behavior, better YOLO26 export coverage, and a handful of platform and integration fixes that make day-to-day workflows smoother.
If you use FastSAM, export models often, or are deploying YOLO26 across different runtimes, this is a great update to pick up. You can explore the release on the v8.4.81 release page and review every change in the full changelog.
Highlights
FastSAM multiple text prompts no longer crash
A key fix in this release resolves a ValueError in FastSAMPredictor.prompt() when passing multiple text prompts.
This affected common prompt-based segmentation workflows, especially when smaller masks were filtered before prompt matching. With the new vectorized index remapping, prompt lists such as ["a photo of a dog", "a photo of a person"] now work as expected.
Implemented in PR #24952 by @ahmet-f-gumustas from @ahmet-f-gumustas 
Export precision handling is now clearer and stricter
Export behavior has been cleaned up to use quantize= consistently, replacing older internal reliance on half=True and int8=True state.
That means unsupported precision requests now fail clearly instead of silently changing to another precision. A few examples:
- CoreML FP32 stays FP32 when requested
- CPU TorchScript FP16 now raises a clear error
- Format-specific precision support is better documented
This work landed across:
More YOLO26 export smoke-test coverage
YOLO26 is now used more broadly as the main export smoke-test model in CI for several formats, improving confidence around the latest recommended model family.
Included in PR #24957 by @glenn-jocher from @glenn-jocher
Improvements
Export docs got a major accuracy pass
Deployment docs were updated to better explain precision support across formats including CoreML, TorchScript, OpenVINO, MNN, RKNN, TensorFlow formats, ExecuTorch, and Sony IMX500.
This should reduce guesswork and make export decisions much easier for deployers.
Included in PR #24950 by @glenn-jocher from @glenn-jocher
Embedding behavior is more intuitive
model.embed() and model.predict() now play more nicely together. After embedding extraction, a normal prediction call returns standard Results again instead of unexpectedly remaining in embedding mode.
Included in PR #24958 by @glenn-jocher from @glenn-jocher
Safer imports for standard YOLO workflows
SAM/SAM3-related imports are now lazier, helping avoid import-time issues in environments that only need standard YOLO tasks and not SAM dependencies.
This was part of the general reliability work in PR #24949 by @glenn-jocher from @glenn-jocher
Better Windows support for ONNXRuntime C++
The ONNXRuntime C++ example now handles non-ASCII and UTF-8 Windows paths more reliably through safer filesystem path conversion.
Included in PR #24953 by @glenn-jocher from @glenn-jocher
Axelera export reliability improvements
Axelera-related export handling was tightened with:
- a
numpy<=2.3.5pin to avoid broken YOLO26 attention-graph exports - stronger export output validation so suspiciously tiny outputs fail loudly
Covered in:
Documentation updates
Hailo docs clarified
The Hailo docs now more clearly explain that HEF generation is currently a manual ONNX-to-HEF workflow, rather than a direct model.export(format="hailo") target.
The notes were also expanded around hardware and SDK compatibility, plus YOLO11 and YOLO26 guidance.
Updated in:
Bug fixes and maintenance
- Sentry-driven reliability fixes in PR #24949 by @glenn-jocher from @glenn-jocher
- Reduced slow CI Jetson TensorRT coverage for faster, more efficient pipelines in PR #24959 by @glenn-jocher from @glenn-jocher
Why this release matters 
This update is all about making Ultralytics workflows feel more predictable and production-ready:
FastSAM prompting is more reliable- Exports are more trustworthy and transparent
- YOLO26 gets stronger deployment coverage
- Embedding and prediction flows are less surprising
- Platform-specific edge cases are handled better
- Docs are clearer for real-world deployment decisions
Try it out
If you want to upgrade right away, you can install the latest package with:
pip install -U ultralytics
And if you are starting a new project, we recommend using Ultralytics Platform together with YOLO26 for the best current training and deployment experience.
Share your feedback 
Please give v8.4.81 a try and let us know how it works for your workflows, especially around FastSAM prompting, export precision, and YOLO26 deployment. Feedback, bug reports, and edge cases help the whole YOLO community improve faster.
Thanks to everyone contributing fixes, testing exports, and sharing reproducible reports 