Hacker News Reader

I actually had the bootloader error message on my install too (regular intel amd64 CPU), so might be something else

Does the CPU includes something like an fTPM? The documentation also suggests there is an unsoldered TPM included.

As far as I can tell, no. It's a separate footprint on the PCB, not difficult to add if you've done a bit of soldering. I haven't tried that yet.

does Vulkan work? It's a must-have for llama.cpp.

There is a fork of Mesa with some support for the onboard GPU (Immortals G720), but it's not upstream yet and might not be for a while. Some people on the forums have installed various discrete GPUs, which would obviously work (modulo bugs.)

There is also an open source driver for the NPU somewhere (Zhouyi NPU) and some documentation, but nothing in an upstream kernel yet. https://zhouyi-npu-tutorial.readthedocs.io/en/latest/0_radxa...