nPHYN1T3
nPHYN1T3
Again why do you keep ignoring the fact I DO NOT have an PRIME / Optimus setup? For YEARS all you need to denote the GPU is DISPLAY=0. (The XScreen...
Several updates later it no longer complains about CreateSwapChain() but says it's syncing cloud while launching (Cloud is disabled and I have an open ticket about this being constantly re-enabled)...
More updates and zero fix. It's back to an error message again due to it latching on to the wrong GPU. Given this "replaced" CS:GO this now means a game...
$HOME/.cache/lm-studio/models by default
I'm not sure if this is technically the same issue but another thing about the (lack of) persistence is simply there is no real effort by the model to "stay...
I initially wanted to reply "So then how does IT select a GPU?" but it looks like it's using them all in parallel...so gud! OK I got the lms command...
I just wanted to toss in qwen2.5-coder:7b is doing the same thing. In fact it's worse.
In theory this is from qwen2.5 crashes. Deepseek I no longer have any logs. I only seem to have these crashes on "code" focused models. ``` Sep 20 16:35:42 pillar...
After a crash of asking where it came up with two options I tried to expedite the question. After the initial crash asking it the following it would get half...
I'll try but I suspect this is chasing a ghost. In frustration a while ago I fired up qwen and started with STOP CRASHING! and the damn thing worked...too stupid...