Revert "[Feature] GLM5.2 rotation v2 Dspark support"

[Tflowers-0129]

Reverts #15210

• vLLM main: vllm-project/vllm@ba07e4a

[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.

---

Tip

💡 Consider Linking a Related Issue or RFC

Your PR title contains the [Feature] tag, indicating a bug fix or new feature.

Linking a related issue or RFC in the PR description is strongly encouraged — it gives reviewers helpful context and speeds up the review. You can use any of these keywords:

• Fixes #<issue_number>
• Closes #<issue_number>
• Resolves #<issue_number>
• Refs #<rfc_or_issue_number> (for RFCs)

🙏 Thanks for helping us keep the project well-organized!

[gemini-code-assist]

Summary of Changes

Hello, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request reverts the previously implemented 'GLM5.2 rotation v2 Dspark support' feature. The changes involve removing DSpark-specific test suites and associated logic, while refactoring core rotation utility functions to a more appropriate location within the llama_eagle3 model module to maintain better code organization and dependency management.

Highlights

• Feature Reversion: Reverted the previously implemented 'GLM5.2 rotation v2 Dspark support' feature.
• Test Cleanup: Removed DSpark-related end-to-end and unit tests, including the deletion of the test_dspark_speculator unit test file.
• Code Refactoring: Moved rotation-related utility functions (get_rotation_path and get_rotation_matrix) from the general utils module to the llama_eagle3 model module.
• Logic Removal: Removed the custom load_draft_model override in the AscendDSparkSpeculator, simplifying the speculative decoding workflow.

New Features

🧠 You can now enable Memory (public preview) to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize the Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counterproductive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for GitHub and other Google products, sign up here.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

Suggested PR Title:

[Test][Misc] Refactor rotation utility functions and clean up dspark speculator tests

Suggested PR Summary:

### What this PR does / why we need it?
This pull request refactors the `get_rotation_path` and `get_rotation_matrix` utility functions by moving them from `vllm_ascend/utils.py` to `vllm_ascend/models/llama_eagle3.py` and updating all corresponding imports. Additionally, it removes the `load_draft_model` override in `AscendDSparkSpeculator` and cleans up related DSpark speculative decoding tests and configurations.

Feedback:
- In `vllm_ascend/models/llama_eagle3.py`, the `get_rotation_path` function should catch `TypeError` and `AttributeError` in addition to `KeyError` when accessing nested dictionary keys in `quant_description` to prevent potential runtime crashes if the configuration structure is unexpected.

### Does this PR introduce _any_ user-facing change?
No.

### How was this patch tested?
The changes are tested by updating existing unit and end-to-end tests, including refactoring `test_glm5_2_mtp_full_decode_only` to directly assert metrics.

[gemini-code-assist]

If quant_description is None or contains nested values that are not dictionaries (e.g., if "optional" is None), subscripting them will raise a TypeError or AttributeError. Since only KeyError is caught, this can lead to an unhandled exception and runtime crash.

To make this defensively robust, catch TypeError and AttributeError in addition to KeyError.

Suggested change

	try:
	quant_description = quant_config.quant_description
	rotation_relative_path = quant_description["optional"]["quarot"]["rotation_map"]["global_rotation"]
	except KeyError:
	return None
	try:
	quant_description = quant_config.quant_description
	rotation_relative_path = quant_description["optional"]["quarot"]["rotation_map"]["global_rotation"]
	except (KeyError, TypeError, AttributeError):
	return None

[github-actions]

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