Lightweight docker image for inference generation.

Hello All, I am currently using

pytorch/pytorch:2.2.1-cuda12.1-cudnn8-runtime

pytorch/pytorch:2.2.1-cuda12.1-cudnn8-runtime

image for my servreless endpoint. The issue is that my Github action to build and push the docker image fails due

ERROR: Could not install packages due to an OSError: [Errno 28] No space left on device

ERROR: Could not install packages due to an OSError: [Errno 28] No space left on device

Is there any recommended lightweight docker image that I can use?