fix qwen torchair attention PrefillCacheHit

[zhaozx-cn]

What this PR does / why we need it?

Fix qwen torchair attention PrefillCacheHit

Does this PR introduce any user-facing change?

How was this patch tested?

vLLM version: v0.10.1.1
vLLM main: vllm-project/vllm@e599e2c

• vLLM version: main
• vLLM main: vllm-project/vllm@0b9a612

[gemini-code-assist]

Code Review

This pull request fixes an issue with PrefillCacheHit in the torchair attention mechanism. The changes involve correctly updating the instance's key/value cache and slicing the block_tables to remove padding before passing it to the attention kernel. While the changes appear to fix the immediate issue, I have a suggestion to make the cache update logic more robust.

[gemini-code-assist]

The self.key_cache and self.value_cache are used by the PrefillCacheHit attention state. This change correctly updates them when the state is PrefillCacheHit. However, the cache update in lines 375-376 happens for any state that has a kv_cache (e.g., DecodeOnly as well). To make the logic more robust and prevent potential issues if other states start using self.key_cache in the future, it would be better to update self.key_cache and self.value_cache unconditionally whenever the cache is modified. This ensures that self.key_cache and self.value_cache always reflect the latest state of the cache tensors passed into this forward pass.

            self.key_cache = key_cache
            self.value_cache = value_cache

[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

❌ Patch coverage is 0% with 5 lines in your changes missing coverage. Please review.
✅ Project coverage is 74.75%. Comparing base (1bbb20e) to head (99cfc07).
⚠️ Report is 1 commits behind head on main.

Files with missing lines	Patch %	Lines
vllm_ascend/torchair/torchair_attention.py	0.00%	5 Missing ⚠️

❌ Your patch check has failed because the patch coverage (0.00%) is below the target coverage (80.00%). You can increase the patch coverage or adjust the target coverage.

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #2787      +/-   ##
==========================================
- Coverage   74.76%   74.75%   -0.02%     
==========================================
  Files         150      150              
  Lines       20891    20896       +5     
==========================================
  Hits        15620    15620              
- Misses       5271     5276       +5     

Flag	Coverage Δ
unittests	74.75% <0.00%> (-0.02%)	⬇️

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.