perf: run batch on a single PaddleOCR instance - #6
Open
phu54321 wants to merge 1 commit into
Open
Conversation
Batch paddleOCR inference on a single model instance, rather than creating `--jobs` paddleOCR model instance. this seems to utilize GPU much better, and is much more VRAM-sane. Co-authored-by: OpenAI Codex, GPT 5.6 Sol <codex@openai.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Batch paddleOCR inference on a single model instance, rather than creating
--jobspaddleOCR model instance concurrently. This avoids recreating PaddleOCR instance for every page too.This seems to utilize GPU much better, and is much more VRAM-sane.
Caveats: This doesnt support multiprocessing. OCRmyPDF by default uses ThreadPoolExecutor so it would work.