Starstruk Logo MarkStarstruk

v3.4.1

bytebot-ai/bytebotv3.4.1Apr 14, 2026by Bobholamovic

AI Summary

A patch release for PaddleOCR-VL that expands hardware compatibility by adding AMD and Intel Arc GPU support. It also fixes dependency issues for Huawei NPU and KunlunXin XPU, and removes the page limit on Docker Compose services.

Key Highlights

  • Added llama-cpp-server backend support
  • Added AMD GPU and Intel Arc GPU hardware support
  • Fixed dependency issues in PaddleOCR-VL images for Huawei NPU and KunlunXin XPU
  • Removed maximum page limit for PaddleOCR-VL Docker Compose services by default

New Features

  • llama-cpp-server backend support
  • AMD GPU and Intel Arc GPU support
  • Fixed NPU and XPU dependencies
  • Removed page limit in Docker Compose

Full Release Notes

## 2026.4.14 v3.4.1 released

* PaddleOCR-VL adds `llama-cpp-server` backend support.
* PaddleOCR-VL adds AMD GPU and Intel Arc GPU hardware support.
* Fixed dependency issues in the PaddleOCR-VL images for Huawei NPU and KunlunXin XPU*
* For the PaddleOCR-VL Docker Compose service, the default configuration no longer limits the maximum number of pages per request.


## 2026.4.14 v3.4.1 发布

* PaddleOCR-VL 新增 `llama-cpp-server` 后端支持。
* PaddleOCR-VL 新增 AMD GPU、Intel Arc GPU 硬件支持。
* 修复 PaddleOCR-VL 华为 NPU、昆仑芯 XPU 镜像中的依赖问题。
* 对于 PaddleOCR-VL Docker Compose 服务，默认不限制单请求的页数上限。


**Full Changelog**: https://github.com/PaddlePaddle/PaddleOCR/compare/v3.4.0...v3.4.1