zaza89/pipeline

PipelineAI: Real-Time Enterprise AI Platform

HTMLApache-2.0

PipelineAI Quick Start (CPU + GPU)

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

Having Issues? Contact Us Anytime... We're Always Awake.

Slack: https://joinslack.pipeline.ai
Email: help@pipeline.ai
Web: https://support.pipeline.ai
YouTube: https://youtube.pipeline.ai
Slideshare: https://slideshare.pipeline.ai
Workshop: https://workshop.pipeline.ai
Troubleshooting Guide

PipelineAI Community Events

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
PyTorch
Caffe/2
Theano
MXNet
PMML/PFA
Custom Java/Python/C++ Ensembles

Supported Model Runtimes (CPU and GPU)

Python (Scikit, TensorFlow, etc)
Java
Scala
Spark ML
C++
Caffe2
Theano
TensorFlow Serving
Nvidia TensorRT (TensorFlow, Caffe2)
MXNet
CNTK
ONNX

Supported Streaming Engines

Kafka
Kinesis
Flink
Spark Streaming
Heron
Storm

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