add tuner test suite

[yzhou103]

Motivation

Technical Details

Test Plan

Test Result

Submission Checklist

• Look over the contributing guidelines at https://github.com/ROCm/ROCm/blob/develop/CONTRIBUTING.md#pull-requests.

[github-actions]

🏷️ CI Guide

Runs automatically on every PR:

• ✅ Pre-checks (submodule verification, code formatting)
• ✅ Aiter op tests (gfx942 + gfx950)
• ✅ Triton tests (only when aiter/ops/triton/** or related paths are changed)

Extended tests (opt-in via labels):

Label	Tests
ci:triton-355	Run Triton tests on MI355 in addition to MI325
ci:sglang	SGLang integration tests
ci:atom	ATOM benchmark (DeepSeek-R1 + GPT-OSS)
ci:vllm	vLLM benchmark
ci:all	All of the above

Add labels via the sidebar or gh pr edit 2734 --add-label <label>

[Copilot]

Pull request overview

This PR introduces a new op_tests/tuning_tests/ test suite intended to validate the tuner stack at multiple levels (static CSV validation, CPU-only unit tests for tuner infrastructure, and GPU-required end-to-end tuning smoke tests).

Changes:

• Added Level 0 CSV integrity tests for tuned/untuned config files.
• Added Level 1 unit tests for base_tuner utilities and simulated mp_tuner polling-loop behavior.
• Added Level 2 GPU smoke tests that execute several tuner scripts end-to-end and validate output CSVs, plus a small README for running the suite.

Reviewed changes

Copilot reviewed 6 out of 6 changed files in this pull request and generated 1 comment.

Show a summary per file

File	Description
op_tests/tuning_tests/test_csv_validation.py	Level 0: validates tuned/untuned CSV integrity (duplicates, invalid times, etc.).
op_tests/tuning_tests/test_tuner_infra.py	Level 1: CPU-only unit tests for base_tuner helpers (CSV I/O, merge/dedup, calculate, post_process).
op_tests/tuning_tests/test_mp_tuner_logic.py	Level 1: simulated tests for mp_tuner polling loop behavior (timeouts, KeyError, AcceleratorError).
op_tests/tuning_tests/test_tune_pipeline.py	Level 2: GPU-required end-to-end tuning pipeline smoke tests invoking tuner scripts.
op_tests/tuning_tests/init.py	Marks tuning_tests as a package.
op_tests/tuning_tests/README.md	Documents the structure/levels and how to run the new tuning tests.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Copilot]

The new regression tests test_topk_not_leak_across_shapes/test_topk_not_shrink_across_shapes will fail against the current GemmCommonTuner.post_process() implementation: it mutates the topk parameter in-place when a shape has fewer valid candidates (if len(filtered_time) < topk: topk = len(filtered_time)), which then carries over to subsequent shapes. Either include the corresponding fix in aiter/utility/base_tuner.py (use a per-shape k = min(requested_topk, len(filtered_time)) without reassigning topk) or adjust/remove these tests.