[cpu] fix custom op

[youkaichao]

fix #11696 (comment) , didn't notice that cpu op uses the same code path as cuda:

vllm/vllm/model_executor/custom_op.py

Lines 46 to 48 in 6cd40a5

	def forward_cpu(self, *args, **kwargs):
	# By default, we assume that CPU ops are compatible with CUDA ops.
	return self.forward_cuda(*args, **kwargs)

[github-actions]

👋 Hi! Thank you for contributing to the vLLM project.
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 do one of these:

• Add ready label to the PR
• Enable auto-merge.

🚀

[DarkLight1337]

This will be fixed in #11836

[youkaichao]

@DarkLight1337 thanks for the reminder!