Items tagged with “Edge AI”.
CUDA Toolkit 13.0 for Jetson Thor unifies ARM toolchains, enables Unified Virtual Memory, advanced GPU sharing, OpenRM/dmabuf interoperability, NUMA support, and enhanced developer tools for edge AI workloads.
Unified CUDA toolkit for Arm on Jetson Thor with full memory coherence, multi-process GPU sharing, OpenRM/dmabuf interoperability, NUMA support, and better tooling across embedded and server-class targets.
Overview of NVIDIA's co-packaged optics (CPO) platform, highlighting photonics/electronics integration, Micro Ring Modulator, COUPE-based engines, and ecosystem collaboration with TSMC and partners for high-density, energy-efficient data-center interconnects.
Jetson Thor combines edge AI compute, MIG virtualization, and multimodal sensors for flexible, real-time robotics at the edge, with FP4/FP8 acceleration and support for Isaac GR00T and large language/vision models.
This article outlines a systematic evaluation framework for choosing foundation models in Amazon Bedrock, combining theory with practical steps to balance performance, cost, and operational needs.
Overview of how NVIDIA's Blackwell hardware, open source models, and a rich software stack accelerate AI—from data prep to deployment—through broad model/tool availability and end-to-end infrastructure.
Pixel Watch 4 adds a domed Actua 360 display, faster charging, repairable components, Gemini-powered health coaching, Satellite SOS, and on-device AI with the Snapdragon W5 Gen 2 — all aimed at a more capable, long-lasting wearable.
Google formally unveils the Pixel 10, 10 Pro, and 10 Pro XL with Tensor G5, Qi2 charging, PixelSnap magnets, and an emphasis on on-device AI and advanced camera features.
The Nemotron Nano 2 9B is an open enterprise‑grade reasoning model with a Hybrid Transformer–Mamba backbone and a configurable thinking budget, delivering leading accuracy and 6x throughput for edge and hybrid deployments.
Open Nemotron Nano 2 9B delivers leading accuracy and up to 6x throughput with a Hybrid Transformer–Mamba backbone and a configurable thinking budget, aimed at edge, PC and enterprise AI agents.
Overview of NVIDIA's Gamescom 2025 updates: DLSS 4, RTX neural rendering, RTX Kit, NvRTX, ACE AI, and related tooling for scalable, AI-driven gaming experiences.
OpenAI unveils gpt-oss-120b and gpt-oss-20b—two open-weight LLMs designed for strong real-world performance at low cost. Licensed under Apache 2.0, they emphasize reasoning, tool use, and efficient on-device deployment across consumer hardware.
ExecuTorch is Meta’s open-source PyTorch inference framework for on-device ML across its family of apps, delivering lower latency, better privacy, and improved performance on Android and iOS.
Obvio raises $22M in Series A to deploy solar-powered, AI-driven stop-sign cameras that detect serious infractions, process footage on-device, and forward verified violations to municipalities—while enforcing strict data retention and sharing limits.
Gridware has built solar-powered sensor boxes mounted on utility poles that listen for sounds and vibrations to detect outages and grid hazards. On-device AI analyzes signals, then reports to the cloud via cellular or satellite.
TinyAgent shows small language models can be fine-tuned for reliable function calling and edge deployment, using curated synthetic data, an LLMCompiler planner, and a Tool RAG approach to power private, low-latency agentic workflows.
A study demonstrating how small language models can perform accurate function calling at the edge using a curated data pipeline, an LLMCompiler-based planner, and on-device execution with macOS integrations.
Explores how LLMs can augment perception, planning, and scenario generation for autonomous vehicles, highlighting approaches like Talk2BEV and GAIA‑1, while discussing trust, reliability, and deployment considerations.