v3.5.0

ggml-org/llama.cppv3.5.0Apr 21, 2026by Bobholamovic

AI Summary

This release deeply integrates with the Hugging Face ecosystem, supporting 20 major models via the Transformers backend. It introduces document processing capabilities, including converting office formats to Markdown and exporting OCR results to DOCX, alongside a new browser-based inference SDK.

Key Highlights

Deep integration with Hugging Face ecosystem supporting 20 major models.
Flexible switching of inference engines (PaddlePaddle static/dynamic, Transformers).
Support for converting common document formats (Word, Excel, PPT) to Markdown.
PaddleOCR-VL series supports exporting parsing results to DOCX format.
Release of official browser inference SDK PaddleOCR.js for PP-OCRv5.

New Features

Hugging Face model support via Transformers backend.
Document format conversion to Markdown.
DOCX export functionality for PaddleOCR-VL results.
PaddleOCR.js browser inference SDK.

Full Release Notes

## 2026.4.21 v3.5.0 released

* Deeply integrated with the Hugging Face ecosystem, with 20 major models supporting Transformers as the inference backend. Supports flexible switching of inference engines, including PaddlePaddle static graph, PaddlePaddle dynamic graph, or Transformers. 
* Supports conversion of common document formats (Word, Excel, Powerpoint) to Markdown.
* The PaddleOCR-VL series, PP-StructureV3, and PP-DocTranslation support exporting parsing results to DOCX format, making it convenient to view and edit in Word.
* Official browser inference SDK PaddleOCR.js is released, supporting running PP-OCRv5 in the browser.

## 2026.4.21 v3.5.0 发布

* 深度适配 Hugging Face 生态，20 个主要模型支持以 Transformers 作为推理后端。支持灵活切换推理引擎，可选飞桨静态图、飞桨动态图或 Transformers。
* 支持常见文档格式（Word、Excel、Powerpoint）转 Markdown。
* PaddleOCR-VL 系列、PP-StructureV3、PP-DocTranslation 支持将解析结果导出为 DOCX 格式，便于在 Word 中查看和编辑。
* 发布官方浏览器推理 SDK PaddleOCR.js，支持在浏览器中运行 PP-OCRv5。

**Full Changelog**: https://github.com/PaddlePaddle/PaddleOCR/compare/v3.4.1...v3.5.0