Prince Canuma comments

Results 572 comments of


                                            Prince Canuma

mlx_vlm.server loads CPU on Macbook pro m1 pro to 60-75% + /health doesn't work

Could you try with the lastest and let me know if the issue persists?

Support for ERNIE-4.5-VL-28B-A3B-Thinking in MLX-VLM

Hey Ethan Thanks for reaching out! Prince here, I'm the creator and maintainer of MLX-VLM. I have been looking into your latest awesome releases and am happy to adding support...

migrate qwen3omni to MLX

Thanks @ziya32 ! It's gonna take a bit of time because I making omni a first class citizen in mlx-vlm.

fix rope deltas in training

> this is not tested, I will do so when I'm home. Is it ready?

@chigkim I ported this model to [MLX-Audio](https://github.com/Blaizzy/mlx-audio) last night, PR comming later today :) I also mitigated speed issues by using chunking and euler as a ODE option. This gives...

MPS Support

Will work on lowering memory usage later. One more thing, for now it doesn't have the visual it's purely audio to audio :) Let me know if you are interested...