PaddleOCR 3.5 adds Transformers backend for OCR and document parsing
The new 3.5 release lets developers run PaddleOCR’s OCR and document‑parsing models (e.g., PP‑OCRv5, PaddleOCR‑VL 1.5) on a Transformers inference backend, simplifying integration with Hugging Face and PyTorch pipelines. Users can configure dtype, device placement, and attention via engine_config, reducing friction for RAG, Document AI, and other downstream workflows.