[Model][LoRA]LoRA support added for glm-4v

[B-201]

To facilitate Lora support, the language model and VL model have been separated. I tested it locally, but it seems I encountered the same issue as this Comment, where the results from vllm differ slightly from those of transformers. However, there is no issue with loading the Lora model, and the results appear to be reasonable.

[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.

🚀

[jeejeelee]

Thanks for your contribution, LGTM, please add related docs!
ping @DarkLight1337 Could you plz look at this PR,thanks

[DarkLight1337]

Thanks for adding support!

[DarkLight1337]

Oh, I forgot again that we need to update the Supported Models page. Can you open another PR for that? Thanks.

[B-201]

Oh, I forgot again that we need to update the Supported Models page. Can you open another PR for that? Thanks.

Sure, I will open another PR to update the docs.