GPUs and Performance¶
PipelineAI supports GPUs natively throughout the entire platform.
Here are some publically-available resources including Docker images, source code, Nvidia driver and toolkit configuration, videos, slides, and workshop materials that demonstrate PipelineAI's support for GPUs.
PipelineAI maintains a collection of Docker Images with many optimizations already enabled including OpenBLAS, AVX, AVX2, FMA, etc.
ML/AI Model Performance Optimizations¶
Click HERE for examples of optimizing model prediction performance with PipelineAI.
TensorFlow Optimization Example¶
This model is very slow at prediction time.
This model is much faster at prediction time!
Register for PipelineAI Enterprise Edition¶