ptzagk / pipeline

PipelineAI: The Standard Runtime For Every Real-Time Machine Learning and AI Prediction in the Enterprise

PipelineAI Home

PipelineAI Features

Consistent, Immutable, Reproducible Model Runtimes

Each model is built into a separate Docker image with the appropriate Python, C++, and Java/Scala Runtime Libraries for training or prediction.

Use the same Docker Image from Local Laptop to Production to avoid dependency surprises.

Sample Machine Learning and AI Models

Click HERE to view model samples for the following:

• Scikit-Learn
• TensorFlow
• Keras
• Spark ML (formerly called Spark MLlib)
• Xgboost
• PMML/PFA
• Custom Java
• Custom Python
• Model Ensembles

Supported Model Runtimes (CPU and GPU)

• Python
• Java
• Scala
• C++
• Caffe2
• Theano
• TensorFlow Serving (TensorFlow)
• Nvidia TensorRT (TensorFlow, Caffe2)
• MXNet
• CNTK
• ONNX

PipelineAI Quick Start

Train and Deploy your ML and AI Models in the Following Environments:

• Local (Docker)
• Local (Docker + Kubernetes)
• AWS SageMaker (CPU + GPU)

Having Issues? Use our 24x7 Support!

• Slack:
• Email: [email protected]
• Web: https://support.pipeline.ai
• Troubleshooting: Guide

PipelineAI Community Events

• PipelineAI Deep Learning Workshops (TensorFlow + Spark + GPUs)
• Advanced Spark and TensorFlow Meetup (Global)

Advanced PipelineAI Product Features

• Click HERE to compare PipelineAI Products.

Drag N' Drop Model Deploy

Generate Optimize Model Versions Upon Upload

Distributed Model Training and Hyper-Parameter Tuning

Continuously Deploy Models to Clusters of PipelineAI Servers

View Real-Time Prediction Stream

Compare Both Offline (Batch) and Real-Time Model Performance

Compare Response Time, Throughput, and Cost-Per-Prediction

Shift Live Traffic to Maximize Revenue and Minimize Cost

Continuously Fix Borderline Predictions through Crowd Sourcing