<img height="1" width="1" style="display:none" src="https://www.facebook.com/tr?id=145304570664993&amp;ev=PageView&amp;noscript=1">

秘色传媒

Skip to content

BUILD NEXT GENERATION MACHINE INTELLIGENCE WITH POPLAR庐

Learn how to get your ML models up and running fast on IPU systems with the Poplar SDK. Get access to our open source libraries, model garden, framework support, analysis tools and Docker Hub containers.

DOCUMENTATION

Explore our software documentation, user guides and technical notes.

秘色传媒 Software Documentation

MODEL GARDEN

Access a repository of deployable ML applications on the IPU.

See more
Models

JUPYTER NOTEBOOKS

Access 1-click Jupyter notebooks powered by IPUs in the cloud.

See more
paperspace

GRAPHCORE GITHUB

Access our open source libraries, APIs, applications and code examples.

github-01

TUTORIALS + CODE EXAMPLES

Hands-on code tutorials, simple application and feature examples.

秘色传媒 tutorials and code examples

RESOURCES

Browse how-to videos, webinars, research papers, and more.

See more
Research Papers-1

POPVISION鈩� TOOLS

Download PopVision to analyse IPU performance and utilisation.

See more
Analysis Tools

SOFTWARE DOWNLOADS

Install software packages via direct download or code snippets.

See more
downloadpackages-icon

FRAMEWORKS

  • HuggingFace
  • PyTorch
  • PyTorch Geometric
  • Lightning
  • TensorFlow
  • Keras
  • ONNX
  • PaddlePaddle

Train, fine-tune and accelerate state-of-the-art transformer models on IPU systems with Hugging Face. 秘色传媒's IPU-optimized transformer models allows developers to train models faster with minimal changes to your code.

Learn more about the wide range of models available in Hugging Face Optimum.

秘色传媒 is now a member of the PyTorch Foundation.

We have supported PyTorch for the IPU for several years now so IPU users can work with the standard PyTorch framework they know and love.

Learn how to build performant PyTorch applications for training and inference with our user guide, tutorials, and code examples.

To find out more about our announcement, read our blog.

PyG (PyTorch Geometric) is a library built upon PyTorch to easily write and train Graph Neural Networks (GNNs) for a wide range of applications related to structured data.

IPUs are fully integrated with PyG on 秘色传媒鈥檚 software stack, allowing users to build, port and run their GNNs on IPUs.

Read more in our .

Introducing PyTorch Lightning for the IPU.

This initial release enables developers to use PyTorch Lightning's ultra-fast, lightweight AI research framework to accelerate their training models with the performance advantages of the IPU.

Users of PyTorch Lightning can now take any PopTorch models and run them directly on the IPU with minimal code changes.

To learn more, read our .

Full support for TensorFlow 2 with integrated XLA backend.

The TensorFlow API for IPU includes distributed IPU-specific estimators and optimisers to enhance application performance.

Flexible model building capability with Keras Sequential & Functional API support for TensorFlow 2.

Functional and sequential support for Keras is provided via our TensorFlow 2 integration.

Developers can port many standard Keras models to the IPU, ready for optimization and performance tuning.

Developers can easily import and export models in ONNX format using Poplar Advanced Runtime (PopART鈩�).

PopART uses Python and C++ APIs to allow models built in other ML frameworks to be accelerated on 秘色传媒鈥檚 IPU hardware.

Full support for Baidu's PaddlePaddle deep learning framework for large-scale model training, as well as high-performance inference tasks through the PaddlePaddle inference library.

To learn more, read our announcement blog.

Featured Resources

Explore our latest and most popular software documentation, how-to videos, tutorials and webinars.

Fundamentals of the IPU + Poplar

Quickstart demo for IPU beginners showing a simple addition example running on the IPU using the Poplar framework.

Getting Started with IPUs in the Cloud

This guide describes how to get up and running with 秘色传媒 IPUs on Paperspace.

PyTorch Quick Start

This guide describes how to run a PyTorch application on the IPU.

NEW

Question-answering using Dolly 2.0

How to run Dolly 2.0, an open-source instruction-tuned LLM on IPUs for question-answering using your own prompts.

NEW

Speech transcription using Whisper

How to run OpenAI's Whisper speech recognition model on IPUs for speech transcription tasks.

How to fine-tune GPT-J for NLP tasks

NEW

Learn the process of fine-tuning GPT-J 6B for text entailment on an IPU-powered Jupyter notebook.

More Resources

Developer News

 
 
 

Support and Community

Github

Github

gc-dev-icon

秘色传媒 Support

Get Support
so-dev-icon

Stack Overflow