[CI/Build] Only build per_token_group_quant.cu on CUDA

[mgoin]

FIX #21083 (comment)

Refer to the AMD build for testing

[github-actions]

👋 Hi! Thank you for contributing to the vLLM project.

💬 Join our developer Slack at https://slack.vllm.ai to discuss your PR in #pr-reviews, coordinate on features in #feat- channels, or join special interest groups in #sig- channels.

Just a reminder: PRs would not trigger full CI run by default. Instead, it would only run fastcheck CI which starts running only a small and essential subset of CI tests to quickly catch errors. You can run other CI tests on top of those by going to your fastcheck build on Buildkite UI (linked in the PR checks section) and unblock them. If you do not have permission to unblock, ping simon-mo or khluu to add you in our Buildkite org.

Once the PR is approved and ready to go, your PR reviewer(s) can run CI to test the changes comprehensively before merging.

To run CI, PR reviewers can either: Add ready label to the PR or enable auto-merge.

🚀

[gemini-code-assist]

Code Review

This pull request correctly restricts the compilation of per_token_group_quant.cu to CUDA builds only. The changes in CMakeLists.txt are consistent with the project's structure for handling platform-specific code. This is a necessary fix as the source file contains CUDA-specific intrinsics and is not compatible with other backends like ROCm. The change is correct and well-contained.

[yewentao256]

Thanks for the fix!

[mgoin]

Closing in favor of #21393