From Sensor to Cloud: Getting Your Data Off of the Edge
Explore efficient methods for transferring time series data from edge devices to the cloud using open-source tools and InfluxDB platform, enabling seamless analysis and utilization.
Advancing Private Federated Learning - Insights and Innovations from Research
Explore private federated learning techniques, challenges, and real-world applications. Gain insights into Apple's implementation and learn how to start research using open-source tools.
So Moore's Law is Dead - Now What? The Future of AI Processing
Explore the future of AI processing beyond Moore's Law, focusing on innovative architectures designed for demanding ML workloads in finance and other sectors.
Machine Learning on the Edge - From Microcontrollers to Embedded Linux Devices
Explore ML deployment on edge devices, from microcontrollers to embedded Linux systems. Learn about hardware options, model adaptation, and deployment strategies for real-world applications.
Federated Learning in Production: Enabling AI Training with Data Privacy
Explore federated learning's applications, benefits, and implementation requirements for AI training on edge devices with data privacy.
Federated Learning in Production: Enabling AI Training with Data Privacy
Explore federated learning's applications, benefits, and implementation requirements for AI training on edge devices with data privacy.
AWQ for LLM Quantization - Efficient Inference Framework for Large Language Models
Explore Activation-aware Weight Quantization (AWQ) for efficient large language model deployment, reducing memory requirements while preserving performance across domains and modalities.
Azure IoT from Edge to Azure Data Explorer (ADX)
Explore Azure IoT's power with Digital Twin and Data Explorer, gaining insights from real-world applications and field experiences.
AI-Driven Edge to Core Data Pipelines for Retail
Automate AI/ML model deployment in retail with an opinionated solution for continuous release cycles from edge to core data pipelines.
Hitchhiker's Guide to Application Connectivity - DevNation Day: MAD
Explore application connectivity options across clouds and edge, with a guide to assess and choose the right approach for your specific needs.
Breaking Silos with Ansible - Automating Software Infrastructure
Discover how Ansible can unify development and operations, driving holistic automation across software infrastructure for improved efficiency and business value.
From Edge to Cloud: Creating Data Pipelines Using Open-source with Strimzi on Kubernetes
Learn to create data pipelines from edge to cloud using open-source Strimzi on Kubernetes, enabling real-time data streaming across your organization.
Run GenAI Projects at Scale Securely: From the Operating System to the MLOps Platform
Secure and scale GenAI projects across the entire stack, from OS to MLOps platform. Learn key considerations, best practices, and opportunities for highly regulated industries.
Edge at Razorpay: API Gateway for DDoS-Protected, High-Scale Environments
Explore Razorpay's Edge API gateway implementation for scalability, availability, and DDoS protection in high-volume financial transactions. Learn architecture, rate limiting, and machine learning insights.
Modern Edge AI Experiences - Building and Deploying On-Premises AI Applications
Explore on-premises AI solutions for secure, scalable applications using Google Distributed Cloud. Learn to build, deploy, and manage AI models at the edge for improved data security and agile development.
AI and Modernization on Your Terms - Strategies for Innovation
Discover customer-proven strategies for AI-powered innovation using public cloud, edge, and cross-cloud infrastructure. Learn how leaders achieve business outcomes faster in various industries.
Llama 3.2 - Multimodal and Edge Computing Advancements
Explore Llama 3.2's multimodal capabilities, edge computing potential, and performance benchmarks. Learn about its vision-tuned models, lightweight versions, and integration with Ollama.
Live Updates for KVM Hosts: Minimizing Downtime in Cloud Computing
Explore live updates for KVM hosts, enabling kernel and userland updates with minimal downtime. Learn about challenges and benefits for cloud providers using this powerful QEMU feature.
It Worked When I Prompted It - Challenges in LLM Production Deployment
Explore challenges and solutions for deploying LLMs in production, covering design patterns, vector databases, reliability enhancement, and cost management strategies.
Enabling Defense Missions with Local LLMs - Part 2
Explore LeapfrogAI, an open-source toolkit for deploying and managing LLMs in sensitive, regulated environments, addressing challenges in defense missions and air-gapped systems.
What's Next in the HTTP Caching World
Explore advancements in HTTP caching, including new headers, cache flow mechanisms, and server-side improvements for efficient content delivery and performance optimization.