[Bugfix][AMD] Update torch_bindings so that scaled_fp4_quant isn't build on ROCm

[SageMoore]

This should hopefully get the AMD CI green

[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.

🚀

[shajrawi]

Thanks for the quick fix!

[mgoin]

LGTM, are there no changes needed in the cmake file?

[SageMoore]

LGTM, are there no changes needed in the cmake file?

Doesn't look like it. #12784 seems to have done a good job making sure the kernel only gets built on the correct cuda version.

[DarkLight1337]

Please fix the merge conflicts