PaddlePaddle/PaddleX v3.3.11
PaddlePaddle/PaddleX
Captured source
source ↗published Dec 9, 2025seen Jun 26captured Sep 5http 200method plain
v3.3.11
Repository: PaddlePaddle/PaddleX
Tag: v3.3.11
Published: 2025-12-09T12:40:45Z
Prerelease: no
Release notes:
2025.12.9 v3.3.11 released
- Fixed an issue where memory kept increasing during repeated inference.
- Added a new parameter
markdown_ignore_labelsto PP-StructureV3 and PaddleOCR-VL, which controls the element types to be ignored in Markdown output; pipeline outputs now include additional information such as the number of pages and image size. - PaddleOCR-VL now supports controlling whether to merge image blocks through the
merge_layout_blocksparameter. - Supported skipping model source checking via the environment variable
PADDLE_PDX_DISABLE_MODEL_SOURCE_CHECK, resolving model loading lag in offline environments. - Fixed an accuracy issue of the RT-DETR-X model when using PIR-TRT inference with batch size > 1.
- Pre-installed fonts in high-stability deployment images to prevent content loss when rendering PDF pages.
- Added support for safetensors 0.7.0 and removed instructions in the documentation about installing a specific version.
- Added support for MetaX GPUs. @metax666
2025.12.9 v3.3.11 发布
- 修复重复推理时内存持续增长的问题。
- PP-StructureV3 与 PaddleOCR-VL 新增参数
markdown_ignore_labels，用于控制在 Markdown 输出中需忽略的元素类型；产线输出结果中新增文件页数、图像尺寸等信息。 - PaddleOCR-VL 支持通过参数
merge_layout_blocks控制是否对图像块进行合并。 - 支持通过环境变量
PADDLE_PDX_DISABLE_MODEL_SOURCE_CHECK绕过模型源检查，解决离线环境下模型加载卡顿的问题。 - 修复 RT-DETR-X 模型在使用 PIR-TRT 推理且 batch size > 1 时出现的精度问题。
- 在高稳定性部署镜像中预装字体，避免渲染 PDF 页面时出现内容缺失。
- 支持 safetensors 0.7.0，并移除文档中关于安装指定版本的说明。
- 新增对沐曦 GPU 的支持。 @metax666
Full Changelog: https://github.com/PaddlePaddle/PaddleX/compare/v3.3.10...v3.3.11