outlines
outlines copied to clipboard
Make sure that logits are always on the device where the model weights are
The issue was due to the logits always being in device=0, I made it such that the logits generated by the model should always be in the model's device.
What happens when the model is loaded on several GPUs? I think that was the rationale behind pinning the logits to device 0.
Note that this is going to become irrelevant once #926 is merged.