[None][test] Fix MLA import path in attention perf harness

[ruodil]

The DSA builder imported MLA from tensorrt_llm._torch.modules.attention, but the MLA class lives in tensorrt_llm._torch.modules.mla. This made test_dsa_ctx_dispatch fail at collection with ImportError against any wheel. Import MLA from its real module.

Summary by CodeRabbit

• Bug Fixes
  • Updated the attention performance benchmark to use the correct module path for the DSA execution path, improving consistency and preventing import-related issues.

Description

Test Coverage

PR Checklist

Please review the following before submitting your PR:

• PR description clearly explains what and why. If using CodeRabbit's summary, please make sure it makes sense.

• PR Follows TRT-LLM CODING GUIDELINES to the best of your knowledge.

• Test cases are provided for new code paths (see test instructions)

• If PR introduces API changes, an appropriate PR label is added - either api-compatible or api-breaking. For api-breaking, include BREAKING in the PR title.

• Any new dependencies have been scanned for license and vulnerabilities

• CODEOWNERS updated if ownership changes

• Documentation updated as needed

• Update tava architecture diagram if there is a significant design change in PR.

• The reviewers assigned automatically/manually are appropriate for the PR.

• Please check this after reviewing the above items as appropriate for this PR.

GitHub Bot Help

To see a list of available CI bot commands, please comment /bot help.

[ruodil]

/bot skip --comment "skip test as just modifying cases"

[coderabbitai]

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: 512e03e7-ef5a-46bf-8802-3a3986749db7

📥 Commits

Reviewing files that changed from the base of the PR and between 9a8ec05 and d3becf7.

📒 Files selected for processing (1)

• tests/microbenchmarks/attention_perf/attention_perf_harness.py

---

📝 Walkthrough

Walkthrough

The DSA MLA module builder in the attention performance test harness now imports the MLA class from tensorrt_llm._torch.modules.mla instead of tensorrt_llm._torch.modules.attention. This is a single-line import source change with no other logic modifications.

Changes

Import correction

Layer / File(s)	Summary
Update MLA import source tests/microbenchmarks/attention_perf/attention_perf_harness.py	_build_dsa_mla_module switches the MLA class import from tensorrt_llm._torch.modules.attention to tensorrt_llm._torch.modules.mla.

Estimated code review effort: 1 (Trivial) | ~2 minutes

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title is specific and clearly matches the fix to the MLA import path in the attention perf harness.
Description check	✅ Passed	The description explains the issue and fix, but the Test Coverage section is left empty.
Docstring Coverage	✅ Passed	Docstring coverage is 100.00% which is sufficient. The required threshold is 80.00%.
Linked Issues check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check	✅ Passed	Check skipped because no linked issues were found for this pull request.

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests

---

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

[tensorrt-cicd]

PR_Github #58401 [ skip ] triggered by Bot. Commit: d3becf7 Link to invocation

[tensorrt-cicd]

PR_Github #58401 [ skip ] completed with state SUCCESS. Commit: d3becf7
Skipping testing for commit d3becf7

Link to invocation