KumoForecast#

class sdm.models.KumoForecast(cross_channel: bool = True, pretrained: bool = True, device: device | str | None = None)#

Bases: ICLModel

The time series forecasting foundation model from “New NVIDIA NV-Tesseract Time Series Models Advance Dataset Processing and Anomaly Detection”.

../../_images/kumo_forecast_light.png

KumoForecast is a time-series foundation model for multivariate forecasting, with optional historical covariates. Architecturally, it combines patch-based time-series embeddings with a MOMENT transformer encoder and a pretrained forecasting head. Optional cross-channel mixing lets forecasts use dependencies between variates after temporal encoding. The forecasting head predicts the native up to 72-step horizon directly from a 512-step history.

Within the ICLModel protocol, KumoForecast treats rows as ordered time steps. In a default forward pass, x_context contains past-only historical covariates, y_context contains one or more past target series, and x_query is required to be empty.

Parameters:

  • cross_channel (bool) – Whether to mix variates after encoding.

  • pretrained (bool) – Whether to load the pretrained checkpoint.

  • device (torch.device | str | None) – The device.

Capabilities#

Supported Input Semantic Types

numerical

Supported Target Semantic Types

numerical

Supported Prediction Tasks

regression

Multi-Target Support

✅

Context-only Column Support

✅

Related Table Support

❌

Default Recipe#

Recipe(
  features=Standardize(eps=0.0),
  target=Standardize(eps=0.0),
  output=AverageEstimators(),
)