Updates for vllm v0.6.4

[tjohnson31415]

vLLM v0.6.4 has been released. This PR is to make changes to the adapter to support this new release.

TODO: I only noticed this one change and wanted to make a commit out of it. More testing should be done to see if additional changes are needed.

Description

• remove use of deprecated LLMInputs that is now just a type instead of a class REF
• TODO

How Has This Been Tested?

Manually tested by running the changed code with vLLM v0.6.4 installed.

Merge criteria:

• The commits are squashed in a cohesive manner and have meaningful messages.
• Testing instructions have been added in the PR body (for PRs involving changes that are not immediately obvious).
• The developer has manually tested the changes and verified that the changes work

[codecov-commenter]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 62.46%. Comparing base (2c80c72) to head (702ef9a).

Additional details and impacted files

@@           Coverage Diff           @@
##             main     #183   +/-   ##
=======================================
  Coverage   62.46%   62.46%           
=======================================
  Files          28       28           
  Lines        1721     1721           
  Branches      211      211           
=======================================
  Hits         1075     1075           
  Misses        544      544           
  Partials      102      102           

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

---

🚨 Try these New Features:

• Flaky Tests Detection - Detect and resolve failed and flaky tests