Saba Fallah

Quick update: I’ve been working on DeepSeek-OCR implementation for a while. Its architecture is quite unique—particularly the two-ViT-encoder design—which differs from the VL models currently implemented in llama.cpp. Combined with...

@bluebread Yes, I agree — the priority is to get a correct first implementation (including the converter) running, even if it’s CPU-backend-only at the start. And absolutely, happy to continue...

@bluebread Great, can you please open a PR to my branch? PR makes it easier to work on the code together.

**Some update on the state of PR:** https://github.com/ggml-org/llama.cpp/pull/17400 The PR is still a draft and we are still proceeding with development. Good news is that we have solved all the...

@Dogacel FYI: I am using your [Dogacel/DeepSeek-OCR-Metal-MPS](https://huggingface.co/Dogacel/DeepSeek-OCR-Metal-MPS) in development for comparing results. Good job! Thank you

Hello everyone, sorry for the delay, but the work is still in progress, there has been some complications. But I am working hard on finishing the PR.