September 14, 2023

Spectro Cloud’s new Palette EdgeAI™ solution helps organizations realize the potential of AI augmented applications at the edge

The new offering:

  • Enables teams to quickly build, deploy and manage Kubernetes-based AI software stacks, across any number of edge locations 
  • Provides integrated access to AI model marketplaces including Hugging Face, plus Kubeflow and LocalAI model frameworks, simplifying deployment and version control.
  • Delivers distributed training and inference capabilities that enable businesses to maximize utilization of edge resources and accelerate model innovation 
  • Introduces unique two-node fault-tolerant edge Kubernetes architecture that drives hardware cost savings while maintaining high availability

SAN JOSE, Calif.—September 14, 2023—Spectro Cloud today announced Palette EdgeAI to simplify how organizations deploy and manage AI workloads at scale across simple to complex edge locations, such as retail, healthcare, industrial automation, oil and gas, automotive/connected cars, and more. 

Palette’s EdgeAI extends Spectro Cloud’s award-winning core Palette Edge Kubernetes management platform that addresses the unique challenges of deploying and managing edge environments at scale, specifically: 

  • Limited on-site specialist IT expertise at the edge locations 
  • Increased security risk due to the distributed nature of edge infrastructure, software stack and communications. 
  • Inconsistent connectivity 
  • Costly and disruptive operational tasks, including security fixes, feature patches and  updates

With a record number of organizations embracing the potential of running AI workloads at the  edge, these challenges are exacerbated. Gartner1 suggests that “by 2027, deep learning will be included in over 65% of edge use cases, up from less than 10% in 2021”. Activities that are achievable in the data center or cloud, such as deploying daily updates to a large language model (LLM), are costly or even impossible across thousands of devices and locations. Furthermore, the exposed security posture of edge locations is problematic given that AI workloads often handle sensitive data and critical intellectual property. 

“More and more of our customers are exploring AI at the edge as their primary mechanism to deliver modern, rich applications and transform the customer experience”, said Jim Melton, Head of Cloud Strategy & Programs, Digital Velocity, CDW. “The need to simplify deployment and provide comprehensive management for AI-optimized infrastructure at the edge is real and solutions such as Palette EdgeAI squarely addresses those challenges”. 

The new Palette EdgeAI solution offers a rich suite of capabilities to address specific requirements throughout the lifecycle of edge infrastructure and AI software stacks.  It: 

  • Deploys and manages complete AI-ready infrastructure stacks in edge computing environments, from the customer’s preferred OS and Kubernetes distribution, to AI model engines like Kubeflow and LocalAI, including easy “plug-and-play” device onboarding. 
  • Secures edge infrastructure to protect sensitive intellectual property and model data, with hardened configurations, SBOM scans, persistent data encryption and robust access controls. Palette offers FIPS compliance for highly regulated industries
  • Improves model accessibility, with integrated access to model marketplaces, including Hugging Face and an enterprise’s own private repositories. Operators can incorporate their chosen models as part of the AI stack ‘Cluster Profile’, or blueprint.  
  • Makes it easy to deploy models to any number of edge locations automatically with a click. Palette will deploy the model along with the infrastructure stack and regularly reconcile the state of the stack to ensure it is in line with policy. 
  • Enables operators to upgrade and roll back model versions deployed in each edge cluster with a click, including Over-The-Air (OTA), zero-downtime upgrades and designing canary deployments across the edge estate, with advanced model observability. 
  • Simplifies distributed inferencing, enabling organizations to leverage multiple edge nodes for parallel execution and reduced model latency. 
  • Unlocks federated training, accelerating model improvement with on-device learning  using local data. 

Reduces edge infrastructure costs, by enabling workloads to run with high availability even on limited edge hardware. Palette’s unique fault-tolerant architecture allows workloads to be deployed on two-node Kubernetes clusters, instead of the usual three node — a huge saving across multiple sites. 2-node HA now also available on all Palette solutions

“The edge is the natural environment for AI inference workloads,” said Tenry Fu, CEO of  Spectro Cloud. “Our mission is to simplify innovation for our customers and we have been  working with organizations that are already disrupting their industries, reaping the benefits of AI at the edge”. 

In the healthcare sector, RapidAI uses Palette Edge to deploy its AI applications into hospitals, giving clinicians deeper clinical context to quickly and accurately triage and diagnose conditions, such as strokes and embolisms, for better patient outcomes. 

"At RapidAI our business is built on continuous AI innovation, helping clinicians right in the  hospital," said Amit Phadnis, Chief Innovation and Technology Officer at RapidAI. "When it comes to deploying our applications securely and easily to the edge, we trust Spectro Cloud's Palette." 

Palette’s EdgeAI will be generally available in Q4 2023 with rapid future capabilities throughout 2024. 

Today Spectro Cloud also announced a new round of investment, led by Qualcomm Ventures. The investment will accelerate Spectro Cloud’s innovation in edge computing, AI and enterprise infrastructure management. 

“Qualcomm is uniquely positioned within the edge ecosystem and with the adoption of AI, edge has become a necessity,” said Dev Singh, Vice President of Business Development, Qualcomm Technologies, Inc. “Across Industrial, Enterprise, Utilities and Retail, we are seeing a need to dynamically orchestrate AI workloads across edge and the cloud, simplify edge deployments and manage upgrades with no downtime to build the next-generation of resilient, high performing applications.” 

IT leaders are invited to learn more about Palette EdgeAI at a live webinar on Wednesday October 25th, 2023

Read more about Palette EdgeAI here.

1. Emerging Tech: Aligning Benefits to Use Cases and Industry Sectors Is Key to Selling the Value of  Edge AI, Eric Goodness, Gartner, Published 30 May 2023, ID G00778310  

GARTNER is a registered trademark of Gartner, Inc. and/or its affiliates in the U.S. and internationally and  is used herein with permission. All rights reserved.  

About Spectro Cloud and Palette 

Spectro Cloud uniquely enables organizations to deploy and manage Kubernetes in production, at scale. Its Palette enterprise Kubernetes management platform gives platform engineering and DevOps teams effortless control of the full Kubernetes lifecycle even across multiple clouds,  data centers, bare metal and edge environments. Ops teams are empowered to support their  developers with curated Kubernetes stacks and tools based on their specific needs, with granular governance and enterprise-grade security. 

Palette Edge, the award-winning version of Spectro Cloud’s core platform, addresses the  unique challenges of edge environments; lack of IT supervision in conjunction with the complexity of Kubernetes and cloud native stacks, the risk of unauthorized physical access to the device — typically deployed in the field, outside secure data centers; to limited or  intermittent connectivity; or sizing constraints that demand lightweight footprints.  

Palette Edge delivers remote troubleshooting, zero-downtime Over-The-Air rolling upgrades and patch management, even in single-server edge deployments, due to its unique A/B OS partition, multi-node failsafe design and support for both ARM and x86 architectures, including Intel’s  Trusted Platform Module (TPM). More recently, Spectro Cloud collaborated with Intel to raise the industry bar for security from the silicon to the app with the Secure Edge-Native Architecture.  

Co-founded in 2019 by CEO Tenry Fu, Vice President of Engineering Gautam Joshi and Chief Technology Officer Saad Malik, Spectro Cloud is backed by Stripes, Sierra Ventures, Qualcomm Ventures, NEC and Translink Orchestrating Future Fund, Boldstart Ventures, Westwave Capital, Alter Venture Partners, Firebolt Ventures, T-Mobile Ventures and TSG. 

For more information, visit or follow @spectrocloudinc and @spectrocloudgov on Twitter. 

PR contact: Ant Newman -