[Feat]FakeBaseModel for offline eagle; Kimi-K2.5 fixes;

[h-guo18]

What does this PR do?

Adds FakeBaseModel for offline EAGLE training and several Kimi-K2.5 compatibility fixes.

• New: FakeBaseModel — lightweight model that loads only lm_head and embed_tokens from a local checkpoint, avoiding full model weight loading during offline training. Configured via FakeBaseArguments and integrated into load_vlm_or_llm.
• Fix: _find_base_model_parts — support Kimi-K2.5 VLM layout (language_model.model path)
• Fix: offline mode lm_head access and CompressedTensors ignore path
• Fix: Kimi-K2.5 decoder past_key_value/past_key_values argument mismatch
• Fix: rglob for .pt discovery in nested offline data dirs; single-node GPU count respects CUDA_VISIBLE_DEVICES

Type of change: Bug fix, new feature

Testing

Tested offline EAGLE training for Kimi-K2.5 end-to-end.

Before your PR is "Ready for review"

Make sure you read and follow Contributor guidelines and your commits are signed (git commit -s -S).

Make sure you read and follow the Security Best Practices (e.g. avoiding hardcoded trust_remote_code=True, torch.load(..., weights_only=False), pickle, etc.).

• Is this change backward compatible?: ✅
• If you copied code from any other sources or added a new PIP dependency, did you follow guidance in CONTRIBUTING.md: N/A
• Did you write any new necessary tests?: ❌
• Did you update Changelog?: ❌

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.

[coderabbitai]

Important

Review skipped

Draft detected.

Please check the settings in the CodeRabbit UI or the .coderabbit.yaml file in this repository. To trigger a single review, invoke the @coderabbitai review command.

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro

Run ID: 2f885e39-036e-4494-aff0-a4b68650a03d

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

Use the checkbox below for a quick retry:

• 🔍 Trigger review

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Commit unit tests in branch haoguo/fakebasemodel

📝 Coding Plan

• Generate coding plan for human review comments

---

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

Tip

You can validate your CodeRabbit configuration file in your editor.

If your editor has YAML language server, you can enable auto-completion and validation by adding # yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json at the top of your CodeRabbit configuration file.

[codecov]

Codecov Report

❌ Patch coverage is 5.88235% with 16 lines in your changes missing coverage. Please review.
✅ Project coverage is 70.28%. Comparing base (7b34de6) to head (0df75e2).
⚠️ Report is 5 commits behind head on main.

Files with missing lines	Patch %	Lines
modelopt/torch/speculative/utils.py	5.88%	16 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #1052      +/-   ##
==========================================
+ Coverage   70.09%   70.28%   +0.19%     
==========================================
  Files         221      227       +6     
  Lines       25541    25873     +332     
==========================================
+ Hits        17902    18185     +283     
- Misses       7639     7688      +49     

☔ 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.