Toto Open Base 1.0

🚀 Toto-Open-Base-1.0

Toto (Time Series Optimized Transformer for Observability) is a time - series foundation model. It's designed for multi - variate time series forecasting, with a focus on observability metrics. It can efficiently handle high - dimensional, sparse, and non - stationary data commonly found in observability scenarios.

Overview of Toto-Open-Base-1.0 architecture.

🚀 Quick Start

📦 Installation

# Clone the repository
git clone https://github.com/DataDog/toto.git
cd toto

# Install dependencies
pip install -r requirements.txt

💻 Usage Examples

Basic Usage

Inference code is available on GitHub. Here's how to quickly generate forecasts using Toto:

import torch
from data.util.dataset import MaskedTimeseries
from inference.forecaster import TotoForecaster
from model.toto import Toto

DEVICE = 'cuda'

# Load pre-trained Toto model
toto = Toto.from_pretrained('Datadog/Toto-Open-Base-1.0').to(DEVICE)

# Optional: compile model for enhanced speed
toto.compile()

forecaster = TotoForecaster(toto.model)

# Example input series (7 variables, 4096 timesteps)
input_series = torch.randn(7, 4096).to(DEVICE)
timestamp_seconds = torch.zeros(7, 4096).to(DEVICE)
time_interval_seconds = torch.full((7,), 60*15).to(DEVICE)

inputs = MaskedTimeseries(
    series=input_series,
    padding_mask=torch.full_like(input_series, True, dtype=torch.bool),
    id_mask=torch.zeros_like(input_series),
    timestamp_seconds=timestamp_seconds,
    time_interval_seconds=time_interval_seconds,
)

# Generate forecasts for next 336 timesteps
forecast = forecaster.forecast(
    inputs,
    prediction_length=336,
    num_samples=256,
    samples_per_batch=256,
)

# Access results
mean_prediction = forecast.mean
prediction_samples = forecast.samples
lower_quantile = forecast.quantile(0.1)
upper_quantile = forecast.quantile(0.9)

For detailed inference instructions, refer to the inference tutorial notebook.

Advanced Usage

⚠️ Important Note

For optimal speed and reduced memory usage, install xFormers and [flash - attention](https://github.com/Dao - AILab/flash - attention). Then, set use_memory_efficient to True.

✨ Features

• Zero - Shot Forecasting
• Multi - Variate Support
• Decoder - Only Transformer Architecture
• Probabilistic Predictions (Student - T mixture model)
• Causal Patch - Wise Instance Normalization
• Extensive Pretraining on Large - Scale Data
• High - Dimensional Time Series Support
• Tailored for Observability Metrics
• State - of - the - Art Performance on [GiftEval](https://huggingface.co/spaces/Salesforce/GIFT - Eval) and BOOM

📚 Documentation

📋 Model Information

📄 Additional Resources

• Research Paper (To add)
• GitHub Repository
• [Blog Post](#TODO - link - to - blogpost)
• BOOM Dataset

📄 License

The model is licensed under the apache - 2.0 license.

📖 Citation

If you use Toto in your research or applications, please cite us using the following:

@misc{toto2025,
  title={This Time is Different: An Observability Perspective on Time Series Foundation Models},
  author={TODO},
  year={2025},
  eprint={arXiv:TODO},
  archivePrefix={arXiv},
  primaryClass={cs.LG}
}