[Spec Decode] Add Script for converting HF Eagle checkpoint to vLLM compatible checkpoint

[sroy745]

1. Add Script for converting HF Eagle checkpoint to vLLM compatible checkpoint. The script is borrowed from https://gist.github.com/abhigoyal1997/1e7a4109ccb7704fbc67f625e86b2d6d but moving it to the vLLM repo for better source control.
2. Addressed a previous documentation comment about adding num_speculative_tokens and updating the link of the script added in 1 in our .md docs.

#11126

[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]

@LiuXiaoxuanPKU / @llsj14 PTAL when you get a chance

[llsj14]

LGTM 👍

[llsj14]

It would be also nice if you inform the baseline ckpt file should be 'safetensor'. Because in this script, the load_file function is for only safetensors.

[sroy745]

Updated the comment.