v0.2.16

datalab-to/markerv0.2.16Jul 12, 2024by VikParuchuri

AI Summary

A performance-focused release that delivers significant speedups across different hardware backends by adopting more efficient surya models for layout and text detection.

Key Highlights

  • 15% GPU speedup, 3x CPU speedup, and 7x MPS speedup
  • Adopted new surya models for layout and text detection
  • Models are more efficient, resulting in faster processing times

New Features

  • New surya models for layout and text detection

Full Release Notes

This release has a 15% GPU speedup, 3x CPU, 7x MPS.  The speedup comes from new surya models for layout and text detection that are a lot more efficient.

 This is a "best case" speedup, if you need to OCR or do equation recognition, the speedup will be lower.  But it will still be a lot faster.