Add more accelerators for learning

[intexcor]

Description & Motivation

Start with xpu support, which torch officially supports.

Then add huawei tpu support. Although it's more likely that you just need to integrate this code.
https://github.com/lyh1028/ascend_npu_for_pytorch_lightning

And then add support for meta accelerators, als and other companies.

Pitch

No response

Alternatives

No response

Additional context

No response

cc @lantiga @Borda

[zhiyuan1i]

Hi, I have a PR:
#20349

This PR allows registration of third-party plugins with minimal changes, instead of integrating third-party devices directly into lightning. I think this can reduce the burden of lightning integration testing, because there is indeed a lack of CI for third-party devices.

[cunkai]

#20349 Thank you. It runs perfectly on the A770.

https://github.com/IntelLabs/matsciml/blob/66b52803eb52c0b8be7349595446051bc54da1f7/matsciml/lightning/xpu.py

[intexcor]

Hi, I have a PR: #20349

This PR allows registration of third-party plugins with minimal changes, instead of integrating third-party devices directly into lightning. I think this can reduce the burden of lightning integration testing, because there is indeed a lack of CI for third-party devices.

xpu is not a third-party plugin, but an accelerator officially supported by torch, like mps.