Earlier quoted context omitted.
You could always offload some layers to the NPU for lower power use and leave the rest to the GPU. If the latter is power throttled (common for prefill, not for decode) that will be a performance improvement.
Routing in a MoE model might fit.
Lemonade by AMD: a fast and open source local LLM server using GPU and NPU
131–133 of 133 posts
Re: Lemonade by AMD: a fast and open source local LLM server using GPU and NPU
#132Earlier quoted context omitted.
> Been running local LLMs on my 7900 XTX for months and the ROCm experience has been... rough. Just out of curiosity... how so? I only ask because I've been running local models (using Ollama) on my RX 7900 XTX for the last year and a half or so and haven't had a single problem that was ROCm specific that I can think of. Actually, I've barely had any problems at all, other than the card being limited to 24GB of VRAM.…
Did you have complete hardware lockups when VRAM is exceeded? I had quite a few on my 7900XTX with llama.cpp (Arch Linux, various driver versions). Once I dial in the quant and context size that never exceed VRAM, it is stable; before that I swear a lot and keep pressing the hardware reset button.