InfoQ Homepage Edge Computing Content on InfoQ
-
Cloudflare Tests Cache Transcoding to Reduce Storage Requirements
Cloudflare recently described a prototype called Cache Transcoding that compresses eligible cache content, mainly uncompressed text such as HTML, JSON, CSS, and JavaScript, using Zstandard before storing it on disk. The hyperscaler estimates that the approach could provide petabytes of additional effective cache capacity, although broader testing is still needed.
-
Cloudflare Workers Accept Inbound TCP, with gRPC the First Protocol on Top
Cloudflare Workers can now accept inbound TCP connections through a new connect(socket) handler routed via Spectrum, ending an eight-year restriction to HTTP. Containers get full-duplex gRPC in any language, while Workers get unary and server-streaming through automatic gRPC-web translation. Everything is private beta.
-
Cloudflare Introduces Cache Response Rules for Post-Origin Cache Control
Cloudflare recently introduced Cache Response Rules, a rules engine that operates after an origin server responds but before content is written to Cloudflare's cache. Previously, Cache Rules operated only on request attributes. Cache Response Rules add a response phase that evaluates origin responses before they are cached.
-
Google LiteRT-LM Speeds up Local Inference up to 2.2x with Gemma 4 Multi-Token Prediction
LiteRT-LM brings native support for Gemma 4 Multi-Token Prediction (MTP) drafters, enabling up to 2.2x faster inference. The framework is expanding beyond Kotlin and C++ adding support for new Swift and a JavaScript APIs.
-
Gemma 4 Multi-Token Prediction Delivers up to ~3x Faster Token Generation
Gemma 4 can be paired with multi-token prediction (MTP) drafters that use speculative decoding to generate multiple tokens in parallel, allowing the model to verify them in a single pass and achieve up to ~3× faster inference without quality loss.
-
Cloudflare Introduces Flagship: an Edge-Native Feature Flag Service Built on OpenFeature
Cloudflare recently announced the closed beta of Flagship, a new feature flag service built directly into its global edge platform. The service lets teams control feature rollouts and experiment with changes without redeploying code, while evaluating flags locally in Cloudflare Workers rather than calling external flag services.
-
Cloudflare Optimizes Edge Stack for High-Core CPUs instead of Large Cache
Cloudflare recently introduced its Gen 13 servers, marking a shift in how its network handles traffic. Instead of relying on large CPU caches for speed, the company redesigned its software to leverage many more processor cores working in parallel in its latest AMD-based servers.
-
Google Opens Gemma 4 Under Apache 2.0 with Multimodal and Agentic Capabilities
Google has announced the release of Gemma 4, a series of open-weight AI models, including variants with 2B, 4B, 26B, and 31B parameters, under the Apache 2.0 license. Key features include enhanced video and image processing, audio input on smaller models, and extended context windows up to 256K tokens.
-
Google Unveils AppFunctions to Connect AI Agents and Android Apps
In a move to transform Android into an "agent-first" OS, Google has introduced new early beta features to support a task-centric model in which apps provide functional building blocks users leverage through AI agents or assistants to fulfill their goals.
-
"Pick and Mix" Custom Regions: Cloudflare Introduces Fine-Grained Data Residency Control
Cloudflare recently introduced Custom Regions, an expansion of its Regional Services that lets customers precisely define where their data is processed. By selecting specific groups of data centers by country or region, customers can ensure that TLS termination and application-layer processing remain within chosen geographic boundaries for compliance and control.
-
Google Research Open-Sources the Coral NPU Platform to Help Build AI into Wearables and Edge Devices
Coral NPU is an open-source full-stack platform designed to help hardware engineers and AI developers overcome the limitations that prevent integrating AI in wearables and edge devices, including performance, fragmentation, and user trust.
-
CNCF Incubates OpenYurt for Kubernetes at the Edge
OpenYurt, a project incubated by the Cloud Native Computing Foundation (CNCF), extends Kubernetes to edge computing, enhancing performance in locations like IoT sites and branch offices. With a growing community and support from industry leaders, OpenYurt focuses on efficient cluster management while maintaining Kubernetes compatibility, ensuring lower latency and improved reliability.
-
How Cloudflare Migrated Quicksilver to Multi-Level Caching While Serving Billions of Requests
The engineering team at Cloudflare recently shared how they transitioned Quicksilver, their internal global key-value store, to a tiered caching architecture. They described their incremental journey from storing everything everywhere to adopting a distributed caching system, improving storage efficiency while preserving consistency guarantees and low-latency reads at the edge.
-
State Space Models Can Enable AI in Low-Power Edge Computing
At the the 2025 Embedded Vision Summit, Tony Lewis, chief technology officer at BrainChip, presented research done by his company into state space models (SSMs) and how they can provide LLM capabilities with very low power consumption in limited computing environments, such as those found on dashcams, medical devices, security cameras, and even toys.
-
Gemma 3n Available for On-Device Inference Alongside RAG and Function Calling Libraries
Google has announced that Gemma 3n is now available in preview on the new LiteRT Hugging Face community, alongside many previously released models. Gemma 3n is a multimodal small language model that supports text, image, video, and audio inputs. It also supports finetuning, customization through retrieval-augmented generation (RAG), and function calling using new AI Edge SDKs.