Hacker News with Generative AI: Edge Computing

Coral USB Accelerator with Google's Edge TPU (coral.ai)
The Coral USB Accelerator adds an Edge TPU coprocessor to your system, enabling high-speed machine learning inferencing on a wide range of systems, simply by connecting it to a USB port.
Running DeepSeek R1 Models Locally on NPU (windows.com)
AI is moving closer to the edge, and Copilot+ PCs are leading the way. With the availability of cloud hosted DeepSeek R1 available on Azure AI Foundry, we’re bringing NPU-optimized versions of DeepSeek-R1 directly to Copilot+ PCs, starting with Qualcomm Snapdragon X first, followed by Intel Core Ultra 200V and others.
Phison aiDAPTIV+ leverages SSDs to expand GPU memory for LLM training (cnx-software.com)
While looking for new and interesting products I found ADLINK’s DLAP Supreme series, a series of Edge AI devices built around the NVIDIA Jetson AGX Orin platform. But that was not the interesting part, what got my attention was it has support for something called the aiDAPTIV+ technology which made us curious.
NVIDIA Releases Jetson Orin Nano Super (nvidia.com)
The NVIDIA Jetson Orin Nano™ Super Developer Kit is a compact, yet powerful computer that redefines generative AI for small edge devices.
Nvidia Jetson Orin Nano Super: The most affordable generative AI supercomputer (nvidia.com)
The NVIDIA Jetson Orin Nano™ Super Developer Kit is a compact, yet powerful computer that redefines generative AI for small edge devices.
Omnivision-968M: Vision Language Model with 9x Tokens Reduction for Edge Devices (nexa.ai)
Transistor for fuzzy logic hardware: promise for better edge computing (techxplore.com)
Edge computing devices, devices located in proximity to the source of data instead of in large data centers, could perform computations locally. This could reduce latency, particularly in real-time applications, as it would minimize the need to transfer data from the cloud.
Edge Scripting: Build and run applications at the edge (bunny.net)
Lightning-fast global CDN
GDDR7 Memory Supercharges AI Inference (semiengineering.com)
High bandwidth and low latency are paramount for AI-powered edge and endpoints.
How the new Raspberry Pi AI Hat supercharges LLMs at the edge (novusteck.com)
The Raspberry Pi AI HAT+ introduces two performance options: a 13 TOPS model for $70 and a 26 TOPS model for $110, both featuring Hailo AI accelerators for high-performance machine learning tasks.
Un Ministral, Des Ministraux (mistral.ai)
Introducing the world’s best edge models.
Starbase: SQLite on the Edge (starbasedb.com)
Plug & Play SQLite
Serving 70B-scale LLMs efficiently on low-resource edge devices [pdf] (arxiv.org)
Large model inference is shifting from cloud to edge due to concerns about the privacy of user interaction data.
Llama 3.2: Lightweight models for edge devices (twitter.com)
Edge Image Builder (suse.com)
Working at the edge introduces a number of complications not seen in a traditional data center.
Show HN: Nexa SDK – Build powerful and efficient AI apps on edge devices (github.com/NexaAI)
Show HN: We built a knowledge hub for running LLMs on edge devices (github.com/NexaAI)
Debian-Based ELxr Distribution Announced for Edge Deployments (linux-magazine.com)
Running PHP fast at the edge with WebAssembly (wasmer.io)
AI Inference Now Available in Supabase Edge Functions (supabase.com)