[BugFix] Fix the issue where the eagle method for speculative decoding fails to load the model

[yangqinghao-cmss]

…g fails to load the model

What this PR does / why we need it?

Does this PR introduce any user-facing change?

How was this patch tested?

vllm:main
vllm-ascend:main

• vLLM version: v0.10.0
• vLLM main: vllm-project/vllm@ea1292a

[gemini-code-assist]

Code Review

This pull request addresses a bug where the drafter model for the Eagle speculative decoding method would fail to load. The fix correctly moves the model loading call for EagleProposer to be unconditional, ensuring it runs regardless of whether auxiliary hidden state outputs are used. This resolves the issue of the drafter model not being initialized. The change is correct and well-contained.

[github-actions]

👋 Hi! Thank you for contributing to the vLLM Ascend project. The following points will speed up your PR merge:‌‌

• A PR should do only one thing, smaller PRs enable faster reviews.
• Every PR should include unit tests and end-to-end tests ‌to ensure it works and is not broken by other future PRs.
• Write the commit message by fulfilling the PR description to help reviewer and future developers understand.

If CI fails, you can run linting and testing checks locally according Contributing and Testing.

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 76.18%. Comparing base (eb43a47) to head (6242df6).
⚠️ Report is 135 commits behind head on main.

Additional details and impacted files

@@           Coverage Diff           @@
##             main    #2331   +/-   ##
=======================================
  Coverage   76.18%   76.18%           
=======================================
  Files         117      117           
  Lines       13296    13296           
=======================================
  Hits        10129    10129           
  Misses       3167     3167           

Flag	Coverage Δ
unittests	76.18% <ø> (ø)

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ 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.

[wangxiyuan]

Thanks for the PR. I have a pr for spec decode refactor, can you help review that one? #2361 Thanks

[yangqinghao-cmss]

Thanks for the PR. I have a pr for spec decode refactor, can you help review that one? #2361 Thanks

Yes, you have corrected the bug.

[github-actions]

This pull request has conflicts, please resolve those before we can evaluate the pull request.