Skip to content

refactor(benchmark): split execute.py into execute/profiling/accuracy/pipeline #421

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
arekay-nv wants to merge 2 commits into
base: main
Choose a base branch
from
Draft

refactor(benchmark): split execute.py into execute/profiling/accuracy/pipeline #421

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
ac81220
refactor(benchmark): split execute.py into execute/profiling/accuracy…
arekay-nv Jul 17, 2026
5e4cf9d
Merge branch 'main' into refactor/execute-split
arekay-nv Jul 20, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 4 additions & 1 deletion AGENTS.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -178,7 +178,10 @@ src/inference_endpoint/
│ ├── benchmark/
│ │ ├── __init__.py
│ │ ├── cli.py # benchmark_app: offline, online, from-config subcommands
│ │ └── execute.py # Phased execution: setup/run_threaded/finalize + BenchmarkContext; run_benchmark runs the main benchmark (cli._run dispatches run_audit when audit: is set)
│ │ ├── execute.py # Phased orchestration: setup_benchmark/run_benchmark_async/finalize_benchmark + BenchmarkContext; run_benchmark runs the main benchmark (cli._run dispatches run_audit when audit: is set)
│ │ ├── profiling.py # Profiler-trigger protocol (vLLM /start_profile,/stop_profile) + ProfileController (URL derivation + start/stop/payload lifecycle)
│ │ ├── accuracy.py # AccuracyConfiguration + per-dataset scoring (_score_accuracy, OSL/response-count rollups, write_accuracy_results)
│ │ └── pipeline.py # MetricsPipeline: ZMQ + metrics-aggregator/event-logger subprocess lifecycle (start/drain_and_build_report/abort/close) + snapshot→Report
│ ├── audit.py # run_audit() — compliance audit orchestrator (phases → verify → result)
│ ├── probe.py # ProbeConfig + execute_probe()
│ ├── info.py # execute_info()
Expand Down
405 changes: 405 additions & 0 deletions src/inference_endpoint/commands/benchmark/accuracy.py
View file
Open in desktop

Large diffs are not rendered by default.

Loading
Loading