TASO

Visit Tool

TASO is a Coding & Development tool that optimizes deep learning computation graphs. It uses automatically generated and verified graph transformations to discover highly optimized computation graphs, outperforming existing deep learning frameworks by up to 3x.

Claim this tool

3Views

At a glance

Pricing

Open Source

Free tier

Yes

API

Yes

Skill level

Technical

About

What is TASO?

TASO, the Tensor Algebra SuperOptimizer for Deep Learning, significantly enhances the performance of deep neural network models. It achieves this by automatically generating and verifying graph transformations to build a vast search space of computation graphs equivalent to the original DNN model. Employing a cost-based search algorithm, TASO discovers highly optimized computation graphs, leading to up to a 3x performance improvement over graph optimizers in current deep learning frameworks. It supports optimizing pre-trained models in ONNX, TensorFlow, and PyTorch formats, and offers a Python interface for arbitrary DNN architectures. Optimized graphs can be exported to ONNX for use in existing deep learning frameworks, maintaining original model accuracy.

Best used for

Ideal for developers who need to optimize deep learning model inference, accelerate computation graph performance, and explore efficient DNN architectures. Especially valuable for those working with ONNX, TensorFlow, or PyTorch models seeking significant speedups.

Common actions

optimize deep learning models

accelerate DNN inference

transform computation graphs

improve model efficiency

low-code/no-codeworkflowsautomated workflowcollaborationdeepfakeopen-source"AI Agents"face swappinggithub copilot

Capabilities

Key features

Automated graph transformations
Cost-based search algorithm
Optimize ONNX models
Optimize TensorFlow models
Optimize PyTorch models
Python interface for DNNs
Export optimized ONNX

Target Audience

developer

Integrations

onnxtensorflowpytorch

Pricing & Plans

Open Source

Free

FAQs

What kind of performance improvements can I expect with TASO?

TASO can outperform the graph optimizers in existing deep learning frameworks by up to 3x. This is achieved by automatically discovering highly optimized computation graphs through its search algorithm and verified transformations.

Which deep learning frameworks does TASO support for model optimization?

TASO can directly optimize pre-trained DNN models in ONNX, TensorFlow, and PyTorch graph formats. It also provides a Python interface for optimizing arbitrary DNN architectures, offering broad compatibility.

Can optimized models from TASO be used in other deep learning frameworks?

Yes, TASO supports exporting the optimized computation graphs to ONNX format. This allows the optimized models to be directly used as inputs by most existing deep learning frameworks, ensuring interoperability.

Trending

Subcategories trending in Coding & Development

Open Source & Models DevOps & Infrastructure No-Code / Low-Code Testing & QA Backend & APIs Prompt Engineering

Trending

Also listed in

This tool also appears in

AI Agents & Automation › AI Frameworks & Infra Research & Education › Scientific Computing

Explore

Browse AI tools by category

Content & Design Productivity & Business Coding & Development AI Agents & Automation Research & Education Wellness & Lifestyle Career Development Marketing & Growth Data & Analytics Customer Support & CX Finance E-commerce