Amazon Elastic Inference Exafunction

Related Products

  • Runpod
    4.2 out of 5 stars 230 Ratings
    Visit Website for Runpod
  • Compute with Hivenet
    5.0 out of 5 stars 4 Ratings
    Visit Website for Compute with Hivenet
  • IONOS Cloud GPU Servers
    4.6 out of 5 stars 45,816 Ratings
    Visit Website for IONOS Cloud GPU Servers
  • Gemini platform
    4.3 out of 5 stars 1,178 Ratings
    Visit Website for Gemini platform
  • LM-Kit.NET
    4.8 out of 5 stars 29 Ratings
    Visit Website for LM-Kit.NET
  • OpenMetal
    4.4 out of 5 stars 41 Ratings
    Visit Website for OpenMetal
  • Dragonfly
    4.9 out of 5 stars 16 Ratings
    Visit Website for Dragonfly
  • Eurekos
    4.8 out of 5 stars 103 Ratings
    Visit Website for Eurekos
  • Google Cloud Platform
    4.5 out of 5 stars 61,093 Ratings
    Visit Website for Google Cloud Platform
  • InMotion Hosting
    4.6 out of 5 stars 3,265 Ratings
    Visit Website for InMotion Hosting
Amazon Elastic Inference:

About

Amazon Elastic Inference allows you to attach low-cost GPU-powered acceleration to Amazon EC2 and Sagemaker instances or Amazon ECS tasks, to reduce the cost of running deep learning inference by up to 75%. Amazon Elastic Inference supports TensorFlow, Apache MXNet, PyTorch and ONNX models. Inference is the process of making predictions using a trained model. In deep learning applications, inference accounts for up to 90% of total operational costs for two reasons. Firstly, standalone GPU instances are typically designed for model training - not for inference. While training jobs batch process hundreds of data samples in parallel, inference jobs usually process a single input in real time, and thus consume a small amount of GPU compute. This makes standalone GPU inference cost-inefficient. On the other hand, standalone CPU instances are not specialized for matrix operations, and thus are often too slow for deep learning inference.
Exafunction:

About

Exafunction optimizes your deep learning inference workload, delivering up to a 10x improvement in resource utilization and cost. Focus on building your deep learning application, not on managing clusters and fine-tuning performance. In most deep learning applications, CPU, I/O, and network bottlenecks lead to poor utilization of GPU hardware. Exafunction moves any GPU code to highly utilized remote resources, even spot instances. Your core logic remains an inexpensive CPU instance. Exafunction is battle-tested on applications like large-scale autonomous vehicle simulation. These workloads have complex custom models, require numerical reproducibility, and use thousands of GPUs concurrently. Exafunction supports models from major deep learning frameworks and inference runtimes. Models and dependencies like custom operators are versioned so you can always be confident you’re getting the right results.
Amazon Elastic Inference:

Platforms Supported

Windows Not Supported
Mac Not Supported
Linux Not Supported
Cloud Supported
On-Premises Not Supported
iPhone Not Supported
iPad Not Supported
Android Not Supported
Chromebook Not Supported
Exafunction:

Platforms Supported

Windows Not Supported
Mac Not Supported
Linux Not Supported
Cloud Supported
On-Premises Not Supported
iPhone Not Supported
iPad Not Supported
Android Not Supported
Chromebook Not Supported
Amazon Elastic Inference:

Audience

IT teams that need an advanced Infrastructure as a Service solution
Exafunction:

Audience

Enterprises searching for a solution to optimize their deep learning inference workload
Amazon Elastic Inference:

Support

Phone Support Not Supported
24/7 Live Support Not Supported
Online Supported
Exafunction:

Support

Phone Support Not Supported
24/7 Live Support Not Supported
Online Supported
Amazon Elastic Inference:

API

Offers API Not Supported
Exafunction:

API

Offers API Not Supported
Amazon Elastic Inference:

Screenshots and Videos

Exafunction:

Screenshots and Videos

Amazon Elastic Inference:

Pricing

No information available.
Free Version Not Supported
Free Trial Not Supported
Exafunction:

Pricing

No information available.
Free Version Not Supported
Free Trial Not Supported
Amazon Elastic Inference:

Reviews/Ratings

Overall 0.0 / 5
ease 0.0 / 5
features 0.0 / 5
design 0.0 / 5
support 0.0 / 5

This software hasn't been reviewed yet. Be the first to provide a review:

Review this Software
Exafunction:

Reviews/Ratings

Overall 0.0 / 5
ease 0.0 / 5
features 0.0 / 5
design 0.0 / 5
support 0.0 / 5

This software hasn't been reviewed yet. Be the first to provide a review:

Review this Software
Amazon Elastic Inference:

Training

Documentation Supported
Webinars Not Supported
Live Online Not Supported
In Person Not Supported
Exafunction:

Training

Documentation Supported
Webinars Not Supported
Live Online Supported
In Person Not Supported
Amazon Elastic Inference:

Company Information

Amazon
Founded: 2006
United States
aws.amazon.com/machine-learning/elastic-inference/
Exafunction:

Company Information

Exafunction
exafunction.com
Amazon Elastic Inference:

Alternatives

Exafunction:

Alternatives

Amazon Elastic Inference:
Exafunction:
Amazon Elastic Inference:
AWS Neuron

AWS Neuron

Amazon Web Services
Exafunction:
Amazon Elastic Inference:
Exafunction:
Amazon Elastic Inference:
Exafunction:
Amazon Elastic Inference:

Categories

Exafunction:

Categories

AI Inference Supported
Deep Learning Supported
Amazon Elastic Inference:

Integrations

PyTorch Supported
TensorFlow Supported
Amazon EC2 Supported
Amazon EC2 G4 Instances Supported
Amazon Web Services (AWS) Supported
MXNet Supported
Exafunction:

Integrations

PyTorch Supported
TensorFlow Supported
Amazon EC2 Not Supported
Amazon EC2 G4 Instances Not Supported
Amazon Web Services (AWS) Not Supported
MXNet Not Supported
Amazon Elastic Inference:
Claim Amazon Elastic Inference and update features and information
Claim Amazon Elastic Inference and update features and information
Exafunction:
Claim Exafunction and update features and information
Claim Exafunction and update features and information