kstavro
kstavro
I haven't synced the branch yet with all the recent commits, but will of course do if this works out in the end. So, I tried to move more of...
If, by accident, you mistype the dimensions of layers in your `model`, the compiler throws you an error at `model.forward_mut()` which does not hint at all to the actual error...
Coming here after noticing that CPU inference in the llama example over at candle only utilizes 10% of my CPU (AMD Ryzen 5800X3D). As I mentioned over at the candle...