October, 2024 - Namla, a provider of a Cloud Native Edge Orchestration platform, is excited to announce its partnership with Advantech, a leading Edge AI hardware provider and an Nvidia Elite partner, as well as an Intel Titanium IoT Solutions Partner. This collaboration represents a significant milestone in the Edge AI industry, optimizing Edge infrastructure deployment and enabling the full potential of Cloud Native architecture to be harnessed on robust Edge AI hardware.

Namla - Advantech : a combination to scale

The integration of Namla's Edge Orchestration platform with Advantech’s cutting-edge Edge AI appliances, powered by Nvidia Jetson , provides companies with a scalable and reliable infrastructure for their Edge deployments. Namla’s globally adopted Zero Touch Deployment (ZTD) framework streamlines the deployment of Advantech devices at scale, cutting time-to-market and reducing costs by up to 90%. Leveraging a Kubernetes-based orchestration layer, Namla ensures a cloud-native environment for efficiently managing and deploying Edge AI applications across multiple locations, boosting service reliability and uptime.

Namla has also introduced the industry’s first Cloud-Native SD-WAN solution, fully integrated with its orchestration platform and compatible with any hardware, including Nvidia Jetson devices. By utilizing Namla's Cloud-Native SD-WAN on Advantech Edge devices, companies benefit from secure and reliable edge-to-cloud connectivity. This solution enables the seamless distribution of AI applications across distributed locations, optimizing AI pipelines and improving operational efficiency.

“We are thrilled to announce our partnership between Advantech and Namla, combining Advantech's industry-leading Edge AI platforms with Namla's cutting-edge orchestration and SD-WAN software expertise,” said Magic Pao, AVP Advantech. “Together, we are driving the next generation of intelligent edge computing, delivering faster, more agile, and scalable edge AI solutions that transform data into actionable insights in real time. This collaboration is set to transform industries by enhancing operational efficiency and empowering businesses to unlock the full potential of their data at the edge, all while maintaining a focus on sustainability and innovation”

Bringing LLM to the the Edge

The recent release of Nvidia’s VLM and LLM , powered by the NIM framework , has paved the way for new opportunities and applications. With Nvidia accelerating VLM deployment at the Edge—evidenced by the release of Jetpack 6—organizations can now reduce bandwidth consumption, achieve real-time results, and improve data privacy. In response, companies are seeking more efficient management strategies for these deployments. Namla’s Zero Touch Deployment (ZTD) solution enables rapid and seamless onboarding of thousands of Nvidia Jetson-powered Edge AI devices, streamlining deployment processes and enhancing overall efficiency.

Additionally, Namla’s Kubernetes-based Edge clusters enable DevOps teams and AI engineers to seamlessly deploy LLMs and other AI models at the Edge without worrying about the underlying infrastructure. Each Edge device operates like a virtual machine in the cloud, simplifying the deployment process and enhancing scalability.

Namla's SD-WAN secure overlay, established between the cloud and the Edge, not only ensures secure and reliable connectivity for deploying LLMs dynamically but also creates a flat network between cloud nodes and Edge devices. This enables hybrid deployment possibilities, enhancing flexibility and operational efficiency.

Infinite number of use cases

The powerful combination of Namla, Advantech, and Nvidia delivers a groundbreaking solution for large-scale Edge AI deployments. Namla’s cloud-native orchestration platform, paired with its innovative SD-WAN solution that runs on any device, including Nvidia Jetson, sets a new standard for scaling Edge AI.

“At Namla, we are excited to partner with Advantech to deliver cutting-edge edge AI solutions across industries. Our Kubernetes-based platform seamlessly integrates with Advantech's hardware, including Nvidia Jetson and other GPU-based devices, enabling the deployment of AI applications such as Nvidia NIMs and more at the Edge and at scale.” Said Younes Khadraoui, Namla co-founder & CFO.

“This collaboration, he continues, combined with Namla’s Cloud Native SD-WAN, ensures reliable and secure edge-to-cloud connectivity, empowering businesses to unlock real-time insights, drive operational efficiency, and innovate at the Edge, all with the agility and scalability needed to meet the demands of modern industries.”

Safety and Security

Using Namla's Zero Touch Deployment (ZTD) framework, ISVs, SIs, and MSPs can efficiently deploy hundreds of security systems based on Advantech’s specialized NVR hardware across distributed locations. Namla’s cloud-native orchestration transforms the way these organizations manage Edge infrastructure, enabling the dynamic deployment of new security applications on Edge devices without the need for on-site visits or manual configurations.

Deploying AI Safety & Security solutions with Namla

Edge-GenAI

Namla’s compatibility with Nvidia Jetson devices, supplied by Advantech, allows organizations to scale the deployment of generative AI (GenAI) applications at the Edge, like LLMs or VLMs using Nvidia’s NIM or other similar framework. Namla’s Kubernetes based orchestration allows to easily deploy these models at hundred of locations, but also have complete visibility on their performance. Moreover, Namla’s secure & reliable network connectivity allows to build strong MLOps pipeline from edge-to-cloud. This unlocks a range of possibilities, such as dynamic, personalized ad generation, smart retail point-of-sale systems, intelligent assistant or even enhancing video surveillance systems.

Bringing GenAI & LLM to the Edge with Namla

Other use cases

Industry 4.0

AI for Healthcare

Low Latency AI over 5G

The collaboration between Namla, Advantech, and Nvidia marks a significant advancement in Edge AI technology. With Namla’s cutting-edge cloud-native orchestration, ZTD deployment, and SD-WAN capabilities, combined with Advantech’s high-performance hardware powered by Nvidia Jetson, businesses across industries can now scale AI-driven applications at the Edge with unprecedented speed, efficiency, and security. This integration not only reduces deployment time and costs but also opens up limitless possibilities for innovation in sectors such as safety and security, Industry 4.0, generative AI, and low-latency AI over 5G networks. The future of Edge AI is here, offering scalable, reliable, and transformative solutions for enterprises worldwide.

Advantech Edge AI Solutions

Advantech is a trusted hardware partner for leading AI, industrial and networking companies globally. Advantech is Elite NVIDIA partner, holding the highest level of commitment to the partnership, with a unique value proposition offering a scalable range of NVIDIA based platforms from palm-size Jetson devices to optimized edge AI servers that maximize GPU density in a thoughtful industrial design ready to be deployed at the edge. These edge AI devices and servers are ideal for customer premise deployment, to build a consolidated, AI-driven customer edge, to be able to run AI and SD-WAN workloads from cloud to edge seamlessly.

Edge AI Devices

Wide range of scalable and compact, industrial-grade platforms for edge AI applications and powered by NVIDIA® Jetson™ for highly efficient GPU performance.

STAR PRODUCT

MIC-733-AO

AI System Based on NVIDIA® Jetson AGX Orin™

• ● Compact fanless design
• ● Embedded with NVIDIA® Jetson AGX Orin™ up to 275 TOPS
• ● Supports 4 x GbE (optional PoE), 4 x USB 3.2 Gen 2 (10 Gbit/s)
• ● Supports 2 x mPCIe, 2 x Nano SIM slots
• ● Supports Allxon 24/7 remote monitoring and OTA deployment; Azure Certified Devices

Edge AI Servers

Advantech edge servers, equipped with latest processors and leveraging a compact, short-depth design ideal for edge AI applications scalability.

STAR PRODUCT

SKY-620V3

2U Rackmount Intel® 4th/5th Gen Xeon® Scalable High-Density GPU Server

• ● Processor: Dual 4th/5th Gen Intel Xeon Scalable processors
• ● Memory: 16 x DDR5 4800MHz ECC RDIMM/ Intel Optane DC Persistence Memory, up to 2TB
• ● Remote Management: IPMI function support
• ● Expansion: Supporting 4 x PCIe x16 double width cards + 2 x PCIe x16 double width cards or 4 x PCIe x8 single width FH/10.5" + 2 x PCIe x8 single width FH/HL cards
• ● PSU: 2700W 1+1 redundant power supply with 80 PLUS Titanium level certification