In-depth technical articles, high-load system architecture analyses, and practical digital transformation strategies shared directly by Sudo’s engineers and solutions architects.
Data drift is what happens when the distribution of the inputs to a live model slowly moves away from the distribution of the data it was trained on. The model raises no error, the API still returns H...
With PHP-FPM, every request to a Laravel site starts from zero: load the autoloader, read the config, register dozens of service providers, and only then reach the code that does the real work. When t...
MLflow is an open-source platform for managing the machine learning lifecycle: it records every training run, stores the model together with its input signature, names and versions it in a registry, a...
When a request splits into several parallel tasks, such as fetching customer data and order status at the same time, we usually reach for ExecutorService and Future. It works, but it hides a flaw that...
When you run hundreds of websites, the three riskiest operations are usually not incidents but routine requests: deploying a new site, changing the domain of a live site, and moving a site to a differ...
vLLM is an open-source engine for serving large language models (LLMs) at high throughput. It came out of a research group at UC Berkeley and was published through the PagedAttention paper at SOSP 202...
A typical order-processing service is written in the "one thread per request" style: the handler receives a request, calls the database, calls the payment gateway, and returns a result. The code is si...
ONNX (Open Neural Network Exchange) is an open format for storing a machine learning model as a computation graph plus weights, separate from the framework that trained it. An ONNX model runs on ONNX...
Before a website goes live on its real domain, it usually has a demo version where the site owner reviews the design, QA runs tests, and performance is measured. The demo runs on a subdomain such as *...
FastAPI is a Python web framework built on Starlette and Pydantic, and a popular way to turn an AI model into an HTTP service. Getting it to run in a notebook is only half the journey. The other half...
Replacing an old monitoring stack with kube-prometheus-stack usually looks very smooth: the install command reports Install complete, Prometheus comes up, Grafana is reachable, every pod is Running. B...
The Visitor pattern is the most awkward design in the GoF catalog. To total the price of two kinds of products, you write a Visitor interface, add an accept method to every class, and then turn each n...
All articles are displayed
