having trouble with efficiency/speed
took 6 minutes to do an extraction of a simple pdf.... also thought it would handle images better with better captioning and whatnot. wondering what i am doing wrong if someone can help. i can only upload images here... but happy to share the pdf with anyone who cares. i have an rtx 5090 i'm running it with... and it took 6 minutes for this pdf https://papers.ssrn.com/sol3/papers.cfm?abstract_id=5056871 (ml) PS C:\Users\xxxxxxxxx> docling --to md --pipeline vlm --vlm-model granite_docling -v $pdf_path --output "C:\Users\xxxxxxx\Documents\Python Scripts\docling_test\out"
2025-10-02 21:11:31,049 - INFO - Loading plugin 'docling_defaults'
2025-10-02 21:11:31,051 - INFO - Registered ocr engines: ['easyocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract']
2025-10-02 21:11:31,060 - INFO - paths: [WindowsPath('C:/tmp/tmphx7vtdt2/ssrn-5056871.pdf')]
2025-10-02 21:11:31,069 - INFO - detected formats: [<InputFormat.PDF: 'pdf'>]
2025-10-02 21:11:31,100 - INFO - Going to convert document batch...
2025-10-02 21:11:31,100 - INFO - Initializing pipeline for VlmPipeline with options hash 14b35a24912cc09d5c7735b8ff9d88c1
2025-10-02 21:11:31,111 - INFO - Loading plugin 'docling_defaults'
2025-10-02 21:11:31,111 - INFO - Registered picture descriptions: ['vlm', 'api']
2025-10-02 21:11:31,128 - INFO - Accelerator device: 'cuda:0'
2025-10-02 21:11:32,998 - INFO - Processing document ssrn-5056871.pdf
2025-10-02 21:18:10,215 - INFO - Finished converting document ssrn-5056871.pdf in 399.16 sec.
2025-10-02 21:18:10,215 - INFO - writing Markdown output to C:\Users\ishan\Documents\Python Scripts\docling_test\out\ssrn-5056871.md
2025-10-02 21:18:10,231 - INFO - Processed 1 docs, of which 0 failed
2025-10-02 21:18:10,235 - INFO - All documents were converted in 399.17 seconds.
We have also this problem performance, would be big help if has a fix or solution