tune_mcs#

nvmolkit.autotune.tune_mcs(
mols: Sequence[Mol],
pairs: Sequence[Sequence[int]],
*,
atom_compare: str = 'elements',
bond_compare: str = 'order',
match_valences: bool = False,
match_formal_charge: bool = False,
ring_matches_ring_only: bool | None = None,
atom_ring_matches_ring_only: bool | None = None,
bond_ring_matches_ring_only: bool | None = None,
timeout_seconds: int = 0,
gpuIds: Iterable[int] | None = None,
calibration_set: Iterable[int] | None = None,
calibration_fraction: float = 0.1,
calibration_max_size: int = 2000,
target_seconds_per_trial: float = 10.0,
n_trials: int = 30,
search_space_overrides: dict[str, Any] | None = None,
cpu_budget: int | None = None,
sampler: Any = None,
seed: int | None = None,
verbose: bool = False,
) TuneResult#

Tune MCSConfig for an explicit-pair, GPU-required MCS workload.

Search semantics are fixed across trials; only execution settings in MCSConfig are tuned. calibration_set contains indices into pairs.