fix(benchmarks): require AIPerf 0.12 for traffic bursts - #767
afourniernv wants to merge 1 commit into
Conversation
Signed-off-by: Alex Fournier <afournier@nvidia.com>
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: Path: .coderabbit.yaml Review profile: CHILL Plan: Enterprise Run ID: 📒 Files selected for processing (5)
Included review availability: Your plan provides up to 12 included reviews per hour; 10 remain after this review. WalkthroughChangesAIPerf version update
Priority: ⬇️ Low Estimated code review effort: 1 (Trivial) | ~5 minutes Merge Risk: ⚪ Minimal · up to The version update is consistently reflected across validation, installation guidance, documentation, and fixtures, so the change is ready to merge. 🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
Full details: Docstring CoverageExplanation Docstring coverage is 50.00% which is insufficient. The required threshold is 80.00%. Docstring coverage is scoped to functions touched by this diff. Analyzed 4 functions across 4 files. (1 skipped: 1 unsupported.)
A rabbit checks the version line Comment |
What
Update the benchmark version guard, install hints, documentation, and fixtures from AIPerf 0.11.0 to 0.12.0.
Why
SWITCH-1517
The traffic-burst profile already emits
--request-rate-series, but the pinned AIPerf 0.11.0 rejects that option before sending a request. AIPerf 0.12.0 supports the existing command and schedule format.Notes for reviewers
The behavior change is the shared supported-version constant. The other edits keep the install guidance and test fixtures aligned. There are no runtime or public API changes.
Live checks against the synthetic backend:
Local validation:
uv run pytest tests/test_aiperf_runner.py tests/test_routing_performance_report.py -quv run pytest tests/ --ignore=tests/e2e --ignore=tests/test_nemo_gym_run.py -quv run ruff check .uv run mypy switchyardcd docs && make publishSummary by CodeRabbit