[Refactor] Refactor Ascend attention implementation forward

[yiz-liu]

What this PR does / why we need it?

This PR refactors the Ascend attention implementation to align with vLLM's core interfaces, simplifying the code and improving maintainability.

Key Changes:

• Align with vLLM's Attention Interface: The forward method signature in AscendAttentionBackendImpl now matches the base AttentionImpl in vLLM, removing the custom trace_flag.

• Enable Opaque Attention Operator: By adding opaque_attention_op to AscendPlatform, we allow vLLM to wrap our attention kernel in its standard vllm.unified_attention_with_output operator. This avoids the need for a custom call path.

• Remove Obsolete Code:

  • The custom op vllm.unified_ascend_attention_with_output has been deleted as it is now redundant.
  • The trace_flag and its associated logic were removed, reducing code complexity.
  • An outdated quantization branch within the attention implementation was cleaned up.

• Improve Readability: Renamed output variables (output vs. intermediate_output) and added comments to clarify the in-place nature of the attention output.

Does this PR introduce any user-facing change?

None.

How was this patch tested?

No extra tests needed.

• vLLM version: v0.11.0rc3
• vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.0

[gemini-code-assist]

Code Review

This pull request refactors the Ascend attention implementation by removing the unified_ascend_attention_with_output custom operator and its associated graph-splitting logic, aligning the attention mechanism more closely with the upstream vLLM framework. This is a positive change for code simplification and maintainability. However, the review identifies a critical issue where support for INT8 KV cache quantization appears to have been removed without a replacement, which could be a significant regression for quantized models.

[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.

[yiz-liu]

Due to CI infra update, we need to close this PR and create a new one.