[perf] overlap page preprocessing, pack the vit, enable prefill CUDA graph for paddle-ocr (#35318)

Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
2026-08-19 08:20:55 +08:00
parent 64e404263e
commit 77fc5c128e
13 changed files with 1278 additions and 265 deletions
@@ -1,7 +1,6 @@
 ---
 title: Unlimited-OCR
 description: "Deploy Baidu Unlimited-OCR with SGLang for long document OCR using prefill-aware sliding-window attention."
-tag: NEW
 ---

 ## Deployment