Skip to main content
Version: 1.44

Supported Versions

This article describes the supported versions and compatibility with supported ML frameworks. For some frameworks, links to example repositories on Gitlab are included. These example repositories can be used to create example deployments on Deeploy.

Deeploy version1.29.0 - 1.31.x1.32.0 - 1.37.x1.38.0 - 1.41.x1.42.0+
KServe0.9.00.11.00.12.00.13.1
Python3.7 - 3.93.8 - 3.113.8 - 3.113.9 - 3.11

Model Frameworks​

The versions described in the following sections are the recommended versions on which the model images have been built. If you deviate from the version, check for potential compatibility issues.

PyTorch​

Pytorch default imagepytorch/torchserve-kfs:0.6.0pytorch/torchserve-kfs:0.8.0pytorch/torchserve-kfs:0.9.0
torch1.7.12.0.02.1.0
torchserve0.7.00.8.00.9.0
torch-model-archiver0.7.00.8.00.9.0

Tensorflow​

Tensorflow default imagetensorflow/serving:2.6.2tensorflow/serving:2.6.2
tensorflow2.6.22.6.2

XGBoost​

XGBoost default imagekserve/xgbserver:v0.9.0kserve/xgbserver:v0.11.0kserve/xgbserver:v0.12.0+
xgboost1.5.01.7.52.0.3

Scikit-learn​

Scikit-learn default imagekserve/sklearnserver:v0.9.0kserve/sklearnserver:v0.11.0+
scikit-learn1.0.11.3.0
joblib1.1.01.3.1

LightGBM​

LightGBM default imagekserve/lgbserver:v0.9.0kserve/lgbserver:v0.11.0+
lightgbm3.3.23.3.2

Huggingface​

Triton server default image-kserve/huggingfaceserver:v0.12.0+
huggingface-hub->=0.14.0,<1.0.0

NVIDIA Triton​

Triton server default image-nvcr.io/nvidia/tritonserver:23.05-py3
triton-2.34.0
pytorch-2.0.0
onnx-1.15.0
tensorrt-8.6.1.2
tensorflow-2.12.0

Custom model Docker images​

Deeploy version<1.32.01.32.x - 1.37.x1.38.x - 1.41.xCloud & 1.42.0+
deeploy-cli-> 1.35.0>= 1.38.0>= 1.42.0
kserve0.9.00.11.00.12.00.13.1

Standard Explainers​

Tree SHAP​

Deploy a tree SHAP explainer without training it yourself. Available only for tree-based classification models when using the XGBoost, Scikit-learn, or LightGBM model frameworks.

Saliency​

Deploy a saliency based explainer without training it yourself. Available only for text generation and text-to-text generation models when using the Hugging Face model framework.

  • Supported standard model frameworks: Huggingface
  • Supported schema: v1
  • Original prediction returned in /explain request: yes

Attention​

Deploy a attention based explainer without training it yourself. Available only for text generation and text-to-text generation models when using the Hugging Face model framework.

  • Supported standard model frameworks: Huggingface
  • Supported schema: v1
  • Original prediction returned in /explain request: yes

Trained Explainer Frameworks​

The versions described in the following sections are the recommended versions for the specific frameworks to use. If you deviate from the version, check for potential compatibility issues. Moreover, for each explainer (version) you can find whether the prediction is returned alongside when making request at the /explain. This can prevent doing redundant requests to obtain prediction seperately.

SHAP​

Deeploy version<1.32.0Cloud & 1.32.0+
shap0.36.00.42.1
dill0.3.30.3.7
original prediction returnedyesyes

Anchors​

Deeploy version<1.32.0Cloud & 1.32.0+
alibi0.6.40.9.4
dill0.3.30.3.7
original prediction returnednono

MACE​

Deeploy version<1.32.0Cloud & 1.32.0+
omnixai1.1.41.3.1
dill0.3.30.3.7
original prediction returnednono

PDP​

  • Expected pre-trained explainer artefact: dill (explainer.dill)
Deeploy version<1.32.0Cloud & 1.32.0+
omnixai1.1.41.3.1
dill0.3.30.3.7
original prediction returnednono

Custom explainer Docker images​

Deeploy version<1.32.01.32.0 - 1.37.x1.38.0 - 1.41.xCloud & 1.42.0+
deeploy-cli-> 1.35.0>= 1.38.0>= 1.42.0
kserve0.9.00.11.00.12.00.13.1
original prediction returnedcustomcustom

Transformer Frameworks​

Custom transformer Docker images​

Deeploy version<1.32.0v1.32.0 - v1.37.xv1.38.0 - 1.41.xCloud & v1.42.0+
deeploy-cli-> 1.35.0>= 1.38.0>= 1.42.0
kserve0.9.00.11.00.12.00.13.1