[BugFix][Core] Fix BlockManagerV2 when Encoder Input is None

[sroy745]

This PR addresses an issue encountered with certain encoder-decoder models, e.g. Llama-3.2-11B-Vision-Instruct, where encoderInput is set to None. This situation arises in the following test cases:

tests/models/encoder_decoder/vision_language/test_mllama.py::test_models[5-128-bfloat16-sizes0-meta-llama/Llama-3.2-11B-Vision-Instruct]
tests/models/encoder_decoder/vision_language/test_mllama.py::test_models[5-128-bfloat16-sizes4-meta-llama/Llama-3.2-11B-Vision-Instruct]

Currently, these tests function correctly with BlockManagerV1 because, when encoder_input is None during the allocation of cross_block_table, an empty BlockTable is created without any blocks. However, this behavior does not hold for BlockManagerV2, where the addition of a BlockTable and attempts to allocate blocks for an empty or None encoder_input lead to assertion failures.

We make the following changes in this PR:

1. For cases where encoder_input is None, we create an empty BlockTable, similar to the behavior in BlockManagerV1, but without adding any blocks to the BlockTable.
2. We have removed two assertions in BlockManagerV2 that pertain to free blocks and the calculation of physical_block_ids. These assertions check whether the BlockTable is empty, which is valid given the use case. The removal of these assertions will not impact the functionality of the BlockManager.
3. With these changes, we are re-enabling BlockManagerV2 for encoder-decoder models.

FIX #9099
FIX #9084

[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.

🚀

[sroy745]

@comaniac / @heheda12345 PTAL when you get a chance

[comaniac]

LGTM

[heheda12345]

LGTM too.