Run LLM benchmark models in parallel (+ configurable --benchmark-parallel)#76
Open
dalmia wants to merge 2 commits into
Open
Run LLM benchmark models in parallel (+ configurable --benchmark-parallel)#76dalmia wants to merge 2 commits into
dalmia wants to merge 2 commits into
Conversation
Refactor the agent-connection LLM benchmark to reuse run_benchmark_cli so models run in parallel (tee'd per-run logs, shared leaderboard/summary), and add a --benchmark-parallel flag / CALIBRATE_LLM_BENCHMARK_PARALLEL env var (precedence: flag > env > default 2) via resolve_benchmark_parallel. Co-authored-by: Cursor <cursoragent@cursor.com>
|
You have reached your Codex usage limits for code reviews. You can see your limits in the Codex usage dashboard. |
main() now drives models through _run_models via run_benchmark_cli, so the
TestLLMBenchmarkMain tests must patch _run_models (returning the {model:
result} mapping) instead of the now-unused run() wrapper. Restores error-path
SystemExit detection.
Co-authored-by: Cursor <cursoragent@cursor.com>
Codecov Report❌ Patch coverage is
📢 Thoughts on this report? Let us know! |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
run_benchmark_cliso models run in parallel with a shared logfile, leaderboard, and consolidated summary (previously one model at a time).--benchmark-parallelflag andCALIBRATE_LLM_BENCHMARK_PARALLELenv var, resolved viaresolve_benchmark_parallel(flag > env > default 2).Changes
calibrate/llm/_output.py,calibrate/llm/__init__.py,calibrate/llm/benchmark.py: parallel model runner +run_benchmark_cliscaffolding.calibrate/utils.py:resolve_benchmark_parallel+DEFAULT_BENCHMARK_PARALLEL.calibrate/cli.py: agent-path refactor + LLM--benchmark-parallelwiring.tests/llm/test_benchmark.py,tests/llm/test_init_extra.py,tests/test_cli.py.Test plan
uv run pytest tests/llm/test_benchmark.py tests/llm/test_init_extra.py tests/test_cli.pyNote: shares the
resolve_benchmark_paralleladdition inutils.pywith the STT/TTS benchmark-parallel PR; whichever merges second needs a trivial rebase.Made with Cursor