thanks, the model itself is a pretty vanilla gpt model based heavily on karpathy's nanogpt, so should not need too many bells and whistles to get it running on specific architectures. that said i have very little experience with platform specific development, so would looove some help from the community :)

Could you stick a torch.compile in the inference and training code, maybe gated behind a flag? This should help AMD/Nvidia performance (and probably other vendors soon) significantly.

PyTorch themselves used nanoGPT training as demo for this: https://pytorch.org/blog/accelerating-large-language-models/

A serious nod to Karpathy here. They could have chosen any other Transformer architecture, but chose perhaps the most reachable one - in the literal sense.

Would the same apply to a GGML port or are the architechtures too different?