Wallaroo SDK AWS Sagemaker Install Guide
How to install the Wallaroo SDK in AWS Sagemaker
The following guides demonstrate how to install the Wallaroo SDK in different environments. The Wallaroo SDK is installed by default into a Wallaroo instance for use with the JupyterHub service.
The Wallaroo SDK requires Python 3.8.6 and above and is available through the Wallaroo SDK Page.
The following ML Model versions and Python libraries are supported by Wallaroo. When using the Wallaroo autoconversion library or working with a local version of the Wallaroo SDK, use the following versions for maximum compatibility.
Library | Supported Version |
---|---|
Python | 3.8.6 and above |
onnx | 1.12.0 |
tensorflow | 2.9.1 |
keras | 2.9.0 |
pytorch | Latest stable version. When converting from PyTorch to onnx, verify that the onnx version matches the version above. |
sk-learn aka scikit-learn | 1.1.2 |
statsmodels | 0.13.2 |
XGBoost | 1.6.2 |
MLFlow | 1.30.0 |
The following data types are supported for transporting data to and from Wallaroo in the following run times:
Runtime | BFloat16* | Float16 | Float32 | Float64 |
---|---|---|---|---|
ONNX | X | X | ||
TensorFlow | X | X | X | |
MLFlow | X | X | X |
Runtime | Int8 | Int16 | Int32 | Int64 |
---|---|---|---|---|
ONNX | X | X | X | X |
TensorFlow | X | X | X | X |
MLFlow | X | X | X | X |
Runtime | Uint8 | Uint16 | Uint32 | Uint64 |
---|---|---|---|---|
ONNX | X | X | X | X |
TensorFlow | X | X | X | X |
MLFlow | X | X | X | X |
Runtime | Boolean | Utf8 (String) | Complex 64 | Complex 128 | FixedSizeList* |
---|---|---|---|---|---|
ONNX | X | ||||
Tensor | X | X | X | ||
MLFlow | X | X | X |
How to install the Wallaroo SDK in AWS Sagemaker
How to install the Wallaroo SDK in AzureML
How to install the Wallaroo SDK in Azure Databricks
How to install the Wallaroo SDK in Google Vertex
How to install the Wallaroo SDK in typical environment