ReleaseBaidu (ERNIE)Baidu (ERNIE)published Nov 25, 2025seen Jun 26

PaddlePaddle/PaddleX v3.3.7

PaddlePaddle/PaddleX

Open original ↗

Captured source

source ↗
GH
GitHub/github.com/PaddlePaddle/PaddleX
PaddlePaddle/PaddleX v3.3.7
Source ↗
published Nov 25, 2025seen Jun 26captured Sep 5http 200method plain

v3.3.7

Repository: PaddlePaddle/PaddleX

Tag: v3.3.7

Published: 2025-11-25T09:39:52Z

Prerelease: no

Release notes:

2025.11.5 v3.3.7 released

  • PaddleOCR-VL now supports inference on DCU and XPU.
  • Optimized the installation process for vLLM / SGLang plugins: hardware information is automatically detected and the matching version of flash-attn is installed without manual installation.
  • The high-stability serving solution for General OCR and PP-StructureV3 pipelines now supports handling concurrent requests in a single instance.
  • For high-stability serving, the server now prints the log IDs of each request in a batch when receiving requests, making debugging easier.
  • The PP-StructureV3 and PP-DocTranslation pipelines now support saving results in DOCX and LaTeX formats.
  • Simplified PDF page rendering logic to improve reading performance. @mara004

2025.11.5 v3.3.7 发布

  • PaddleOCR-VL 新增对 DCU 和 XPU 的推理支持。
  • 优化 vLLM / SGLang 插件的安装流程：自动检测硬件信息并安装匹配版本的 flash-attn，无需手动安装。
  • 通用 OCR 与 PP-StructureV3 产线的高稳定性服务化部署方案新增支持单实例并发请求处理。
  • 对于高稳定性服务化部署，服务器在接收请求时新增打印 batch 内各请求的 log ID，便于调试。
  • PP-StructureV3、PP-DocTranslation 产线新增结果保存为 DOCX、LaTeX 格式的能力。
  • 简化 PDF 页面渲染逻辑，提升读取性能。 @mara004

Full Changelog: https://github.com/PaddlePaddle/PaddleX/compare/v3.3.6...v3.3.7