Clean up Docker images on HPU and CPU benchmarks

[huydhn]

HPU runners ran out of space with all the Docker images it downloaded https://github.com/pytorch/pytorch-integration-testing/actions/runs/19330939614/job/55293605542

Testing

https://github.com/pytorch/pytorch-integration-testing/actions/runs/19347827069

cc @louie-tsai @xuechendi

[yangw-dev]

why it is download in the first place, if those docker images are unused at this point? It just download all of them , and only use some? curious about this, but will approve

[huydhn]

They are from previous jobs running on the same runner. This is a common issue for non-ephemeral runners where docker pull keeps piling up the images it uses over time. On our pet instances like H100, we have a daemon to clean up these images running on the server, so you don't see this step on CI. In this case, HPU servers are from Intel, so they are not set up in the same way

[xuechendi]

Thanks so much for the PR, I just acknowledged the issue this morning and cleaned up HPU now.
However, I found issue is not image not deleted(I have a cronjob to do so), but the docker container is never stopped after benchmark