deepseek-ai
/

DeepSeek-OCR

Image-Text-to-Text

feature-extraction

vision-language

Model card Files Files and versions

Make infer general, so it runs on non cuda devices

#6

by aamirshakir - opened Oct 20, 2025

base: refs/heads/main

←

from: refs/pr/6

Discussion Files changed

Infer hard codes .cuda(), which does not allow it to run on CPU or other devices, instead use self.device so it can run on CPU, MPS etc.

Make infer general, so it runs on non cuda devices155d104f

Ah, linting, sorry let me update it.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

Ready to merge

This branch is ready to get merged automatically.

· Sign up or log in to comment