Blaize Code-Free Tooling To Accelerate the ‘AI Edge’ Application Lifecycle

Blaize is shipping an open and code-free platform to help companies more quickly and easily build and deploy AI Edge apps and workflows.  AI Studio sports features to enable even less technical staff to design and deliver AI edge projects in as little as days.

Tags: AI, app lifecycle, Blaize, DevOps, edge, MLOps,

Blaize is shipping an open and code-free platform to help companies build AI Edge apps and workflows.  The AI Studio platform is designed to accelerate the full AI lifecycle - from idea, build, deploy and manage.

 

The Blaize approach aims to reduce from months to days the time needed to go from models to deployed production applications, according to company execs.

 

“While AI applications are migrating to the Edge with growth projected to outpace that of the Data Center, Edge AI deployments today are complicated by a lack of tools for application development and MLOps,” says Dinakar Munagala, Co-founder and CEO, Blaize.  

 

“AI Studio was born of the insights to this problem gained in our earliest POC edge AI hardware customer engagements, as we recognized the need and opportunity for a new class of AI software platform to address the complete end-to-end edge AI operational workflow,” Munagala added.

 

Blaize vice president for R&D Dmitry Zakharchenko added details about the company’s tooling AI Studio, noting it is open and highly optimized for ‘edge’ AI development projects across heterogeneous ecosystems.  

 

“With the AI automation benefits of a truly modern user experience interface, AI Studio serves the unique needs in customers’ edge use cases for ease of application development, deployment, and management, as well as broad usability by both developers and domain expert non-developers,” Zakharchenko said.

 

Among Blaize’s AI Studio features are:

 

Code-free assistive UI for more users, more productivity: The AI Studio code-free visual interface is intuitive for a broad range of skill levels – not only AI data scientists. This ease of use enables AI edge app development among a wider set of employees, even those unskilled in AI. Users can include AI developers, system builders and even non-technical business domain subject matter experts.

 

Open standards for user flexibility, broader adoption:  AI Studio users can deploy models with one click plug into any workflow across popular open standards, including ONNX, OpenVX, containers, Python, or GStreamer. This degree of open standard deployment allows AI Studio to deploy to any hardware that fully supports the standards.

 

Marketplaces collaboration: AI Studio supports open public models, data marketplaces and repositories. Further, it provides connectivity and infrastructure to host private marketplaces. This enables users to easily and continually scale and reuse their proven AI edge models and vertical AI solutions. Via AI Studio’s compatibility with marketplaces and repositories, users also have the option to access hundreds of proven models with simple drag and drop, which speeds application development.

 

Easy-to-use application development workflow: The AI Studio model development workflow allows users to easily train and optimize models for specific datasets and use cases, and deploy quickly into multiple formats and packages. With the click of a button, AI Studio’s distinctive Transfer Learning feature quickly retrains imported models for the user’s data and use case. In addition, users can easily build and customize complete application flows other than neural networks, such as image signal processing, tracking or sensor fusion functions.

 

Optimized edge MLOps/DevOps features: As a complete end-to-end platform, AI Studio helps users deploy, manage, monitor and continuously improve their edge AI applications. Built on a cloud-native infrastructure based on microservices, containers and Kubernetes, AI Studio is highly scalable and reliable in production.

Blaize AI Studio Early Adopter Customers Results

Blaize’s existing AI Edge tools and technologies are already in use for smart retail, smart city and industry 4.0 markets. To date, documented results show Blaize customers are realizing new efficiencies for their AI application development and deployment.

 

Examples include:

  • Complete end-to-end AI development cycle reduction from months to days
  • Reduction in training compute by as much as 90%
  • Edge-aware efficient optimizations and compression of models with a < 3% accuracy drop
  • New revolutionary contextual conversational interfaces that eclipse visual UI

 

AI Studio will be generally available in Q1 2021.




back