[V1][VLM] Fix edge case bug for InternVL2

[ywang96]

When there's only one image in the batch, the image_embeds needs to be reshaped to [feature_size, hidden_size] from [num_patches, feature_size_per_patch, hidden_size] before getting unsqueezed.

This was previously not observed during offline mode because the default max_num_batched_tokens=8196 is always bigger than max image size of internVL2, but discovered when running online benchmark with the default max_num_batched_tokens=2048 where chunked prefill is needed.

[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.

🚀