Edge computing
Edge computing is a distributed computing approach that places computation and data processing near the users, devices, or sources and destinations of data.
LLMs in Production
A computing architecture that processes data near its source or point of use to reduce dependence on remote services.
- How it is used
- Motivates local LLM inference when connectivity, latency, or reliance on remote APIs is a concern.
- How deep it goes
- Outlines hardware choices and model-conversion requirements, but advises against training on edge devices.
- Examples
- Uses a Raspberry Pi with a Coral USB TPU and an NVIDIA Jetson board to illustrate hardware and framework trade-offs.
- What you can do after
- Evaluate edge deployment options against connectivity, latency, memory, speed, and hardware constraints.
Fast by Default
Edge computing is the execution of application logic at geographically distributed locations close to users rather than only in centralized data centers.
- How it is used
- Improves globally distributed application delivery by moving computation and rendering closer to users.
- How deep it goes
- Defines edge computation, contrasts it with CDN caching, and gives caching rules plus a measured deployment example.
- Examples
- Uses retailer rendering near German shoppers, Australian image delivery, and Fastly's global news-content purging.
- What you can do after
- Evaluate centralized and edge architectures, then choose caching and rendering placement using latency, personalization, and update frequency.
Digital Twins in Action
Edge computing is a computing architecture that processes data near the device or data source rather than exclusively in a remote cloud.
- How it is used
- Supports digital twins by processing sensor and video data near physical assets and sending selected results onward.
- How deep it goes
- Explains processing and transmission tradeoffs and demonstrates local detection, without implementing selective transmission in the detection listing.
- Examples
- Uses webcam object detection and a battery-powered water meter camera that extracts readings locally.
- What you can do after
- Apply local object detection using a YOLOv8 model and webcam.
Server-Side WebAssembly
Edge computing performs computation near the sources or consumers of data rather than exclusively in centralized cloud infrastructure.
- How it is used
- Places computation near mobile devices, vehicles, sensors, and other data sources to reduce latency and bandwidth usage.
- How deep it goes
- Explains edge requirements through device heterogeneity, resource limits, hardware agnosticism, and deployment trade-offs.
- Examples
- Uses mobile devices, vehicles, sensors, self-driving cars, smart cities, and microcontrollers as deployment contexts.
- What you can do after
- Evaluate whether portable, low-memory execution suits applications distributed across constrained edge devices.
Latency
Edge computing is a computing approach that places computation and data processing near the users or devices that generate or consume the data.
- How it is used
- Reduces geographical and last-mile latency by colocating computation and data with users.
- How deep it goes
- Distinguishes near edge from far edge and explains latency rationale, but does not provide an implementation workflow.
- Examples
- Uses Tokyo–Virginia routing, nearby Cloudflare data centers, and an embedded SQLite REST API.
- What you can do after
- Evaluate near-edge and far-edge placements by their expected effects on geographic and last-mile latency.
Google Anthos in Action
Edge is a distributed computing environment located near the users, devices, or data sources that generate or consume workloads.
- How it is used
- Places latency-sensitive workloads near devices or users to reduce cloud dependence, data transfer, and response time.
- How deep it goes
- Defines deployment categories, fleet-management needs, and a smart-retail architecture, but stops short of installation procedures.
- Examples
- Uses autonomous driving, smart cities, factories, surveillance, augmented reality, remote surgery, and retail queue management.
- What you can do after
- Operate/configure distributed edge architectures that keep real-time processing local and delegate analytics or training to the cloud.
Also covered in
What to know first
- meanThe mean is a measure of central location equal to the arithmetic average of numerical observations, or the probability-weighted average of a random variable’s possible values.
- latencyLatency is the elapsed time between initiating an operation or request and receiving its corresponding result or observable response.
- language modelA language model is a computational model that represents patterns in linguistic sequences to assign probabilities, predict, generate, or evaluate language.
- retrieval-augmented generationRetrieval-augmented generation is a technique that retrieves relevant information from external sources and supplies it as context to a generative model when producing an output.
Related concepts
- edge deviceuses · An edge device is a computing device located near data sources, users, or operations that can process data close to where it is generated or consumed.
- CDNincludes · A content delivery network is a geographically distributed network of servers that caches or delivers digital content from locations near requesting users.
- cloud computingcontrasts with · Cloud computing is a model for on-demand network access to shared computing resources and services that can be provisioned and scaled as needed.
- computer visionused by · Computer vision is the field of computing concerned with extracting and interpreting information from images, video, and other visual data.
- deploymentkind of · Deployment is the process of placing or releasing software, models, or configuration into a target environment so they can operate there.
- meanaddresses · The mean is a measure of central location equal to the arithmetic average of numerical observations, or the probability-weighted average of a random variable’s possible values.
Questions about edge computing
What is edge computing?
Edge computing is a distributed computing approach that places computation and data processing near the users, devices, or sources and destinations of data.
Which Manning books explain edge computing?
LLMs in Production, Fast by Default, Digital Twins in Action, Server-Side WebAssembly, Latency and Google Anthos in Action.
What should I know before learning edge computing?
Manning books that teach edge computing usually introduce mean, latency, language model and retrieval-augmented generation first.
What is the difference between edge computing and cloud computing?
Edge computing is a distributed computing approach that places computation and data processing near the users, devices, or sources and destinations of data. Cloud computing is a model for on-demand network access to shared computing resources and services that can be provisioned and scaled as needed.
What kinds of edge computing are there?
Kinds of edge computing include CDN.
What is edge computing a kind of?
Edge computing is a kind of deployment. Deployment is the process of placing or releasing software, models, or configuration into a target environment so they can operate there.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.





