[Cleanup] Remove dead code make_attention_mask function

[LICO1314]

What this PR does / why we need it?

This PR removes the unused make_attention_mask function from vllm_ascend/worker/v2/attn_utils.py.

Why it's dead code:

• After PR [Refactor] Fix AttentionMaskBuilder singleton and remove redundant pcp_prefill_mask #4870 (attention mask unification refactor), attention mask generation has been centralized in the AttentionMaskBuilder singleton class
• The mask is now generated directly by metadata builders when needed (e.g., AscendAttentionMetadataBuilder, AscendMLAMetadataBuilder)
• The make_attention_mask function is no longer called anywhere in the codebase
• The function's parameters (including attn_mask and spec_attn_mask) were also removed from build_attn_metadata in the same refactor

Changes:

• Remove make_attention_mask function (24 lines) from vllm_ascend/worker/v2/attn_utils.py

Does this PR introduce any user-facing change?

No. This is a code cleanup that removes dead code. No user-facing behavior changes.

How was this patch tested?

• Verified that make_attention_mask is not called anywhere in the codebase (via grep)
• CI tests pass to ensure no regressions
• The function has been unused since PR [Refactor] Fix AttentionMaskBuilder singleton and remove redundant pcp_prefill_mask #4870 was merged
• vLLM version: v0.13.0
• vLLM main: vllm-project/vllm@2f4e654

[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.

[gemini-code-assist]

Code Review

This pull request is a good cleanup effort to remove the make_attention_mask function, which has become dead code. The change is correct based on the provided context. However, the cleanup seems incomplete as the removal of this function leaves another function and a global variable as dead code. I've added a comment to address this.

I am having trouble creating individual review comments. Click here to see my feedback.

vllm_ascend/worker/v2/attn_utils.py (151-171)

While removing the make_attention_mask function is correct, it appears this was the only function using get_attn_mask_builder. As a result, get_attn_mask_builder and the global variable _ATTENTION_MASK_BUILDER are now also dead code and should be removed as part of this cleanup to make it complete.

Specifically, you should also remove:

• The _ATTENTION_MASK_BUILDER global variable.
• The get_attn_mask_builder function.
• The from vllm_ascend.attention.attention_mask import AttentionMaskBuilder import, which will become unused.