v3.3.5
·
46 commits
to release/3.3
since this release
2025.10.23 v3.3.5 released
- Fixed the issue with weight data type mapping, supporting GPUs with compute capability between 7 and 8.
- Resolved the problem of model configuration parsing failure when the model configuration includes
quantization_config. - Fixed the issue where inference errors occurred when using paths containing Chinese characters in directories on Windows.
- Resolved the problem of being unable to use PaddleOCR-VL models hosted on the AI Studio platform.
- Added support for passing the
max_new_tokensparameter during PaddleOCR-VL model inference.
2025.10.23 v3.3.5 发布
- 修复权重数据类型映射问题,支持 compute capability 在7-8之间的GPU。
- 修复模型配置中包含
quantization_config时模型解析配置失败的问题。 - 修复 Windows 环境下,使用带有中文目录的路径推理报错的问题
- 修复无法使用 AI Studio 平台托管的 PaddleOCR-VL 模型的问题
- 支持 PaddleOCR-VL 模型推理时
max_new_tokens参数的传入
Full Changelog: v3.3.4...v3.3.5