when using your fork, it worked https://github.com/fensoft/rk3528-tvbox

I am currently at 7.0.0-rc1. I can upload my jump-start image so you can check if my kernel build works with your device. If you like what you see, it is only a 'prepare-jump-start ${target-mount-point}' away to install the kernel package alongside your existing system. I know about it, but since it is just another not mainline solution with another dependency mess, I am not particularly interested.

Good afternoon, I can't compile the cores for this TV box. https://paste.armbian.com/ziyasupeka

I agree with you. Neural network works well on NPU. I tried to load tiny llm model, but it's still too large for NPU. The bottleneck is the sram in NPU, not computing capacity. And I found an interesting project https://github.com/NotPunchnox/rkllama

Thanks for the replies. But I've decided on Linux Mainline on ARM Chromebooks (Veyron): https://github.com/velvet-os/imagebuilder/releases/tag/251115-02 which at least works from the SD card. I'm still working on the installation. 😉