Skit5
Skit5
> Experiment with max memory and set it lower until it fills more of the other GPU first. It will come back around once it reaches your 2nd gpu's limit....
I tried, even after upgrading to the latest version of the driver (535->550), but it still loads ~67% on GPU1 then starts loading in GPU0 up to ~93%. I don't...
Glad to see I'm not the only one with this complaint. Although it's really a Transformers issue. With Llama_cpp (using gguf), I can fully load it. But then that's limiting...
Ticket opened on HF Transformers as it's probably an issue on their side: https://github.com/huggingface/transformers/issues/32412
Thank you @oskirby for your quick response! You will find the logs here below. Anything else I can provide to you? ``` [10.02.2025 07:24:14.982] Debug: QQuickRootItem(0x5fb62eb9d390, parent=0x0, geometry=0,0 0x0 🖼)...
Was something changed on your side? Because I made an upgrade (mostly kernel stuff) and tried just now to open it; the screen actually displayed something.
> I pay for this service and cannot use it the last 4 month on my laptop because it is in the state described in this ticket. I want to...