mineru-4.0.8-released
QwenLM/Qwen3-VLmineru-4.0.8-releasedSep 27, 2026by myhloli
Upgrading?
AI Summary
This release focuses on performance improvements for PDF processing by introducing a native kernel that reuses document render sessions and text snapshots across analysis windows.
Key Highlights
- Native PDF kernel for improved performance and reduced character-level regrouping
- Cross-window reuse of document render sessions and text snapshots
- Dependency upgrade to docvortex 0.5.2
Breaking Changes
- docvortex dependency upgraded from 0.4.x to 0.5.x
New Features
- Direct consumption of native span content without character-level reorganization
Full Release Notes
## 更新内容 / What's Changed **性能 / Performance** - PDF 原生内核：跨分析窗口复用文档渲染会话与文本快照，原生 span 内容与赋值直接消费、免去字符级重组 / Native PDF kernel: reuse document render sessions and owned text snapshots across analysis windows; consume native span content and assignments without character-level regrouping **依赖 / Dependencies** - docvortex 提升至 0.5.2（0.4.x → 0.5.x）/ Require docvortex>=0.5.2 (0.4.x → 0.5.x) **Full Changelog**: https://github.com/opendatalab/MinerU/compare/mineru-4.0.7-released...mineru-4.0.8-released
Related Repositories
rasbt/LLMs-from-scratch★ 107,043
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
lyogavin/airllm★ 40,153
AirLLM 2.8T LLM inference with single 4GB GPU
NirDiamant/RAG_Techniques★ 29,958
This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial.
microsoft/OmniParser★ 25,539
A simple screen parsing tool towards pure vision based GUI agent
karpathy/nn-zero-to-hero★ 24,906
Neural Networks: Zero to Hero