add GitHub CI for Intel GPU

[faaany]

Summary

This PR adds the dependencies for using liger-kernel on XPU and adds the workflow.yml.

Testing Done

Test done on local XPU machine. To make all tests pass, we need to first merge PR #535 first.

• Hardware Type: Intel(R) Data Center GPU Max 1550
• run make test to ensure correctness
• run make checkstyle to ensure code style
• run make test-convergence to ensure convergence

[faaany]

@ByronHsu @sywangyi @yao-matrix

[faaany]

• @mgrabban

[ByronHsu]

Is this ready to merge? How to enable our project to find linux-max1550-gpu-8? Do we need to give you some api key?

[faaany]

Is this ready to merge? How to enable our project to find linux-max1550-gpu-8? Do we need to give you some api key?

Yes, the code is ready to merge. But we still need to configure the self-hosted runner for Liger-Kernel Repo. Maybe @hebiao064 can help with that?

[faaany]

We also need to merge this PR first #498 to make the CI green on XPU, since the issue on triton-xpu might take some time to get fixed (see intel/intel-xpu-backend-for-triton#3237).

[ByronHsu]

Thank you! Just merged #498. And @hebiao064 will work with you on setting on self-hosted runner!