Programming, architecture, application development, message queues, middleware, databases, containerization, big data, image processing, machine learning, AI, personal growth.
This article explains the concept, architecture, and step‑by‑step implementation of Retrieval Augmented Generation (RAG), covering indexing, retrieval & generation processes, a practical LangChain‑Redis‑llama.cpp example on Kubernetes, code snippets, test results, challenges, and references.
This article answers ten common Kubernetes questions, covering pod scheduling strategies, OOM behavior, dynamic ConfigMap updates, pod stability, ClusterIP service load balancing, log collection, liveness probes, scaling mechanisms, exec access, and troubleshooting container restarts, providing concise explanations for each scenario.
This article explains how Kubernetes Extended Resources let you define custom resource types, describes the creation, synchronization, and scheduling workflow, highlights the non‑real‑time allocatable status behavior, and discusses practical limitations and the role of Device Plugins and Operators.
This article explains the core Kubernetes Node lifecycle—including registration, status updates, lease management, heartbeat mechanisms, and health monitoring—detailing how kubelet interacts with the API server, configuration options, and node-controller behavior for handling failures and graceful node shutdown.
This article explains how Kubernetes, through the Kubelet and CRI components such as containerd and cri‑o, pulls container images, stores them on the node, and performs periodic garbage collection based on configurable age and disk‑usage thresholds.
This article explains how to construct a ChatGPT‑like conversational system by detailing the core dialogue flow, adding session and history management with a database, defining REST APIs, and exploring extensions such as caching, elastic scaling, and production‑ready deployment considerations.
This article walks through the complete process of fine‑tuning both domain‑specific and large‑language translation models on Kubernetes documentation, covering data preparation, model selection, training configurations, the differences between Seq2Seq and CausalLM, and how LoRA can dramatically reduce resource usage while improving performance.
This article explains how Kubernetes manages and schedules GPU resources by introducing the Device Plugin framework, the Container Device Interface (CDI), Node Feature Discovery (NFD), and the GPU Operator, detailing their workflows, APIs, and practical usage with NVIDIA GPUs.
The author chronicles the challenges and solutions of running large language models locally using Ollama, experimenting with cloud GPUs on Google Colab, managing Python dependencies through Docker, and ultimately fine‑tuning a small Qwen model, providing a practical guide for AI enthusiasts.
This article provides a comprehensive overview of Ollama, a lightweight tool for running large language models, detailing its client‑server architecture, local storage layout, and the step‑by‑step workflow of user interactions with the model.
