Starstruk Logo MarkStarstruk

mineru-4.0.4-released

Significant-Gravitas/AutoGPTmineru-4.0.4-releasedSep 19, 2026by myhloli

Upgrading?

What changed from autogpt-platform-beta-v0.8.0 → mineru-4.0.4-released?What's new in v1.5.84 after mineru-4.0.4-released?

AI Summary

This update optimizes GPU memory usage for high-VRAM devices, refines logging levels to reduce noise, and fixes filename handling in the WebUI. It also updates the mineru-vl-utils dependency to address lmdeploy multi-frame response issues.

Key Highlights

  • Optimized GPU memory utilization logic for high-VRAM devices
  • Scoped log-level flag to server-side logs only
  • Fixed filename stemming logic for long filenames (>120 bytes)
  • Updated mineru-vl-utils to fix lmdeploy multi-frame response issues

New Features

  • GPU memory utilization optimization
  • Scoped log-level to server-side logs
  • Idempotent filename stemming for WebUI

Full Release Notes

## 更新内容 / What's Changed

**修复 / Fixes**
- VLM 引擎：高显存设备上 GPU memory utilization 逻辑优化 / engine: adjust GPU memory utilization logic for high-VRAM devices
- 日志降噪：推理性能、模型加载与原生表格优先级日志由 info 降为 debug / Lower inference performance, model loading and native table priority logs to debug
- API server：`--log-level` 仅作用于服务端日志，不再影响其他组件 / Scope `--log-level` to server-side logs only
- WebUI：超长（>120 字节）文件名的收敛处理幂等化，重复保存不再截断 / Make filename stemming idempotent for >120-byte filenames

**依赖 / Dependencies**
- mineru-vl-utils 最低版本提升至 2.0.5（含 lmdeploy 引擎多帧响应不完整的修复）/ Require mineru-vl-utils>=2.0.5 (fixes incomplete lmdeploy multi-frame responses)

**Full Changelog**: https://github.com/opendatalab/MinerU/compare/mineru-4.0.3-released...mineru-4.0.4-released

Related Repositories

public-apis/public-apis★ 491,227

A collective list of free APIs

NousResearch/hermes-agent★ 256,100

The agent that grows with you

yt-dlp/yt-dlp★ 200,275

A feature-rich command-line audio/video downloader

microsoft/markitdown★ 191,565

Python tool for converting files and office documents to Markdown.

langgenius/dify★ 159,235

Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.