make eagle embedding optional

[yeyu-nvidia]

What does this PR do?

New feature

Overview:
This PR adds a flag in eagle config: use_embedding. By default it is set to True. If set to False, eagle does not use embedding. It only takes the hidden_states from previous tokens to predict the next hidden_states. Draft tokens are predicted at the end by calling lm_head on all hidden_states.

Usage

# Add a code snippet demonstrating how to use this

Testing

Before your PR is "Ready for review"

• Make sure you read and follow Contributor guidelines and your commits are signed.
• Is this change backward compatible?: Yes/No
• Did you write any new necessary tests?: Yes/No
• Did you add or update any necessary documentation?: Yes/No
• Did you update Changelog?: Yes/No

Additional Information

[copy-pr-bot]

Auto-sync is disabled for draft pull requests in this repository. Workflows must be run manually.

Contributors can view more details about this message here.

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 74.64%. Comparing base (a703e22) to head (d4248bd).
⚠️ Report is 5 commits behind head on main.

Additional details and impacted files

@@            Coverage Diff             @@
##             main     #589      +/-   ##
==========================================
+ Coverage   74.45%   74.64%   +0.19%     
==========================================
  Files         182      183       +1     
  Lines       18250    18389     +139     
==========================================
+ Hits        13588    13727     +139     
  Misses       4662     4662              

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

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.