[TPU host offload] delta load optimization for tpu connector local

[saikat-royc]

Description

Start with a short description of what the PR does and how this is a change from
the past.
Handle load of delta tokens

The rest of the description includes relevant details and context, examples:

• why is this change being made,
  1. Accomodate num_computed_tokens reported by vllm when determining
     the number of tokens that need their corresponding kv cache to be
     loaded. This reduces the effective number of tokens that need to be loaded for every unique request.
  2. Supporting unit test cases
• the problem being solved and any relevant context,
• why this is a good solution,
• some information about the specific implementation,
• shortcomings of the solution and possible future improvements.

If the change fixes a bug or a Github issue, please include a link, e.g.,:
FIXES: b/123456
FIXES: #123456

Tests

Existing Unit tests in tests/distributed/ and benchmark tests
Please describe how you tested this change, and include any instructions and/or
commands to reproduce.

Checklist

Before submitting this PR, please make sure:

• I have performed a self-review of my code.
• I have necessary comments in my code, particularly in hard-to-understand areas.
• I have made or will make corresponding changes to any relevant documentation.