Commits · 8033f3ebafc8d73e2b575018f369a429ab8d881b · nexlab / coderai · GitLab

Oct 05, 2026
- ocr: size the VLM share to the measured footprint and cap its batch (v0.2.26) · f25592dc
  Stefy Lanza (nextime / spora ) authored Oct 05, 2026
  f25592dc
Oct 04, 2026
- ocr: hand the card over at a page boundary, so OCR takes turns like any model · 4be32ede
  Stefy Lanza (nextime / spora ) authored Oct 04, 2026
  4be32ede
- ocr: size a VLM engine's vLLM against free VRAM, and never answer 503 (v0.2.25) · b1004ebd
  Stefy Lanza (nextime / spora ) authored Oct 04, 2026
  b1004ebd
Oct 02, 2026
- ocr: olmOCR-2 as an alternative engine, and stop the Surya-2 crash loop (v0.2.24) · 75200c0b
  Stefy Lanza (nextime / spora ) authored Oct 02, 2026
  75200c0b
Sep 16, 2026
- ocr: match the surya the local install actually runs, and stop hiding its errors · 64ac2d05
  Stefy Lanza (nextime / spora ) authored Sep 16, 2026
  64ac2d05
Aug 22, 2026
- ocr: make managed Surya-2 vLLM reclaimable by VRAM eviction · 2c419247
  Stefy Lanza (nextime / spora ) authored Aug 22, 2026
  2c419247
Aug 21, 2026
- ocr: participate in thermal throttling + VRAM eviction · 3a01becb
  Stefy Lanza (nextime / spora ) authored Aug 21, 2026
  3a01becb
- ocr(surya): parse Surya2 (>=0.20) result.blocks[].html + reading order · edf2125a
  Stefy Lanza (nextime / spora ) authored Aug 21, 2026
  edf2125a
- Add vLLM as a first-class managed engine backend (LLM + OCR Surya2) · a5d9fe82
  Stefy Lanza (nextime / spora ) authored Aug 21, 2026
  a5d9fe82
Aug 20, 2026
- ocr: fix PaddleOCR 3.x API + pin surya-ocr to classic local-torch 0.6.4 · 2654d749
  Stefy Lanza (nextime / spora ) authored Aug 20, 2026
  2654d749
Aug 16, 2026
- ocr: non-blocking first-use isolated-venv build (background + 503 retry) · f8b86701
  Stefy Lanza (nextime / spora ) authored Aug 16, 2026
  f8b86701
- Add dedicated OCR subsystem + finalize multi-engine backends · 2485403f
  Stefy Lanza (nextime / spora ) authored Aug 16, 2026
  2485403f