Replies: 1 comment
-
Thanks for the report. #4653 will fix the bug. A workaround for the current version is to freeze the model without a GPU. |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Hello!
I trained a potential function and ran it successfully on the GPU's lammps, but due to GPU memory limitations, I ran lammps on the CPU, but I got an error, which is in the documentation.
I installed it through the following two offline packages:
deepmd-kit-3.0.1-cpu-Linux-x86_64.sh
deepmd-kit-3.0.1-cuda126-Linux-x86_64.sh
Thank you very much for your help!
problem.txt
input.json
in.txt
Beta Was this translation helpful? Give feedback.
All reactions