Shengyu Liu

icon indicating a website link https://interestinglsy.github.io/ icon indicating an email [email protected]

icon company @deepseek-ai , Peking University icon location Peking University, Beijing, China

Results 13 comments of Shengyu Liu

Fail in running Llama-3.2-1B

Could you try to print `rope_scaling_factor`? It should be a `int`, but it seems that it is a `dict` from the error message

peak memory calculation

I don't think so. To answer your question, we should first know how PyTorch manages GPU memory. As far as I know, PyTorch has two allocation modes: either PyTorch allocates...

peak memory calculation

An example: