Xinfer

Latest version: v0.3.2

Safety actively analyzes 688572 Python packages for vulnerabilities to keep your Python projects secure.

Scan your dependencies

Page 1 of 4

0.3.2

New Models
* New Model - BLIP2 Variant mBLIP and BLIP2 flan by dnth in https://github.com/dnth/x.infer/pull/67
* Qwen2 VL Integration by dnth in https://github.com/dnth/x.infer/pull/72

Bugfixes
* Pin dependencies version by dnth in https://github.com/dnth/x.infer/pull/70


**Full Changelog**: https://github.com/dnth/x.infer/compare/v0.3.1...v0.3.2

0.3.1

What's Changed
* Add TOC to README by dnth in https://github.com/dnth/x.infer/pull/65


**Full Changelog**: https://github.com/dnth/x.infer/compare/v0.3.0...v0.3.1

0.3.0

New Features

OpenAI Chat Completion compatible API.
A new endpoint has been added to support OpenAI's Chat Completion functionality

* Add OpenAI Chat Completion endpoint by dnth in https://github.com/dnth/x.infer/pull/61

Gradio Visualization
We've introduced a new feature that allows users to visualize results using Gradio[4](https://github.com/dnth/x.infer/pull/60). This integration provides an intuitive and interactive way to display and explore model outputs, making it easier for users to understand and interpret their results.

* Visualize results in Gradio by dnth in https://github.com/dnth/x.infer/pull/60

New Models

YOLO Seg and Pose
Support for Ultralytics YOLO pose estimation and segmentation models has been added. This expansion of supported models allows users to work with more advanced computer vision tasks. Additionally, we've optimized the fuzzy matching system for unsupported models, improving the overall user experience when working with various model types.

* Suport ultralytics yolo pose and seg model. Optimized fuzzy matching for unsupported models. by 315386775 in https://github.com/dnth/x.infer/pull/52

Bug fixes
* Open browser to fastapi docs page when running model_serve by dnth in https://github.com/dnth/x.infer/pull/54
* Fix soft import to exclude local folder by dnth in https://github.com/dnth/x.infer/pull/64

Breaking Changes

Result Class Abstraction

In this release, we've made a significant change by abstracting model outputs into a Result class. While this may require some adjustments to existing code, it provides a more consistent and robust way of handling model outputs across different types of models and tasks.

* Abstract model outputs into a `Result` class by dnth in https://github.com/dnth/x.infer/pull/58


**Full Changelog**: https://github.com/dnth/x.infer/compare/v0.2.1...v0.3.0

0.2.1

What's Changed
* Support ultralytics classification by 315386775 in https://github.com/dnth/x.infer/pull/44
* Add non blocking calls to Ray Serve by dnth in https://github.com/dnth/x.infer/pull/51

New Contributors
* 315386775 made their first contribution in https://github.com/dnth/x.infer/pull/44

**Full Changelog**: https://github.com/dnth/x.infer/compare/v0.2.0...v0.2.1

0.2.0

What's Changed
* Ray Serve and FastAPI endpoint by dnth in https://github.com/dnth/x.infer/pull/50


**Full Changelog**: https://github.com/dnth/x.infer/compare/v0.1.3...v0.2.0

0.1.3

What's Changed
* Add Phi 3.5 Vision Model by dnth in https://github.com/dnth/x.infer/pull/43


**Full Changelog**: https://github.com/dnth/x.infer/compare/v0.1.2...v0.1.3

Page 1 of 4

© 2024 Safety CLI Cybersecurity Inc. All Rights Reserved.