-
[NA][SDK] Optimizer Benchmarks Refactor (#4178)
frostbyte_neo 发布于
2025-11-23 03:21:00 +00:00 -
Update benchmark_task.py
-
Update logging.py
-
refactor: centralized runner
-
Update budgeting.py
-
chore: lint
-
test: benchmarks
-
test: benchmarks
-
Update test_benchmark_fewshot_live.py
-
refactor: refactor benchmark API
-
refactor: benchmarks
-
refactor: benchmarks
-
chore: types mypy
-
refactor: optimizer benchmarks
-
Create benchmark_worker.py
-
refactor: optimizer benchmarks
-
chore: lint
-
Create __init__.py
-
Update run_benchmark.py
-
Update benchmark_manifest.py
-
chore: types
-
deps: mypy tests for optimizer
-
chore: new lint
-
Update README.md
-
chore: map metrics
-
Update manifest.schema.json
-
fix: tests
-
chore: chatprompt support
-
chore: working examples
-
chore: pre-flight
-
Update benchmark_config.py
-
chore: tests
-
Update README.md
-
Update runner.py
-
Update benchmark_results.py
-
Update run_benchmark_local.py
-
Update task_runner.py
-
chore: short id
-
chore: mypy
-
Update logging.py
-
Update Makefile
-
feat: gepa runs
-
feat: modal finalized
-
chore: metadata for gepa runs
-
fix: modal
-
Update benchmark_config.py
-
Update benchmark_worker.py
-
chore: fix
-
chore: config
-
chore: updated
-
Update README.md
-
Update pupa.py
-
Update tasks.example.json
-
Update README.md
-
Update generator.example.json
-
chore: fix pupa
-
chore: config to match
-
feat: new dataset defaults
-
fix: tests
-
chore: better edge case handling
-
Update sdks/opik_optimizer/benchmarks/modal_utils/__init__.py
Co-authored-by: Copilot 175728472+Copilot@users.noreply.github.com
-
Update pyproject.toml
-
chore: updates
-
Update sdks/opik_optimizer/benchmarks/modal_utils/storage.py
Co-authored-by: Copilot 175728472+Copilot@users.noreply.github.com
-
Update task_runner.py
-
chore: wire dataset test and metrics
-
Update task_evaluator.py
-
Update task_evaluator.py
-
chore: type changes
-
Update .pre-commit-config.yaml
-
Update logging.py
-
Update task_runner.py
-
Update run_benchmark_modal.py
-
Update benchmark_task.py
-
Update gepa_full.generator.json
-
Update worker_core.py
-
chore: finalized benchmarks
-
Update test_benchmark_fewshot_live.py
Co-authored-by: Copilot 175728472+Copilot@users.noreply.github.com
下载附件
-