scoring | pip install -e ".[scoring]" | sympy for symbolic math comparison |
stats | pip install -e ".[stats]" | scipy for confidence intervals, McNemar significance testing, and regression analysis |
skills | pip install -e ".[skills]" | NeMo Skills benchmark integration |
harbor | pip install -e ".[harbor]" | Harbor agent integration (OpenHands, Terminus-2, etc.) |
lm-eval | pip install -e ".[lm-eval]" | LM-Evaluation-Harness integration |
inspect | pip install -e ".[inspect]" | Inspect AI log export (inspect_ai-compatible EvalLog files) |
ray | pip install -e ".[ray]" | Ray distributed launcher |
harnesses | pip install -e ".[harnesses]" | lm-evaluation-harness tasks |
export | pip install -e ".[export]" | WandB and MLflow experiment tracker export |
docs | pip install -e ".[docs]" | Sphinx, NVIDIA theme, mermaid for building docs |
all | pip install -e ".[all]" | Common runtime integrations: scoring, stats, ray, lm-eval, and Harbor |
dev | pip install -e ".[dev]" | pytest, ruff, and common development extras |
