You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
When this happens your driver is compiling the required support to run KoboldCpp, this is normal especially on the CUDA11 version of KoboldCpp. koboldcpp_cu12.exe is faster with this, but unlike what people advice the best solution is actually to leave it open and just do its thing. It will get unstuck once the driver compiled everything it needed to run the CUDA11 version on top of CUDA12.
I have i5-6400, 16gb ram, rtx 3060ti 8gb
i'm trying to load model:
LLaMA2-13B-Tiefighter.Q4_K_S.gguf
i launch program koboldcpp.exe (exactly this version) and setting Gpu Layers to 41 as recommended (on -1 the issue is exactly the same though)
then i click launch, click my model and there's some text, but no vram, memory or cpu usage change has been monitored
the log:
The text was updated successfully, but these errors were encountered: