LinuxProfessional

Fresh content:

Install NVIDIA Drivers and CUDA on Linux Server for AI: The No-Nonsense Guide (2026)

Complete guide to installing NVIDIA drivers and CUDA on Ubuntu 24.04, RHEL 9, and Fedora 41 for AI workloads. Covers open vs proprietary kernel modules, Nouveau blacklisting, Docker GPU runtime, pe...

Install NVIDIA Drivers and CUDA on Linux Server for AI: The No-Nonsense Guide (2026) Complete guide to installing NVIDIA drivers and CUDA on Ubuntu 24.04, RHEL 9, and Fedora 41 for AI workloads. Covers open vs proprietary kernel modules, Nouveau blacklisting, Docker GPU runtime, persistence mode, and power management.

Read more:

Docker Model Runner on Linux: Deploy and Serve AI Models with GPU Acceleration

Use Docker Model Runner on Linux to deploy, serve, and manage AI models with GPU acceleration, including setup, model pulling, API integration, and production deployment patterns.

Docker Model Runner on Linux: Deploy and Serve AI Models with GPU Acceleration Use Docker Model Runner on Linux to deploy, serve, and manage AI models with GPU acceleration, including setup, model pulling, API integration, and production deployment patterns.

New article:

5 Best AI Coding Assistants for the Linux Terminal: Hands-On Comparison

Hands-on comparison of 5 AI coding assistants for the Linux terminal: Claude Code, Aider, Continue, Open Interpreter, and Cline. Covers install, real-world tests, and honest recommendations.

5 Best AI Coding Assistants for the Linux Terminal: Hands-On Comparison Hands-on comparison of 5 AI coding assistants for the Linux terminal: Claude Code, Aider, Continue, Open Interpreter, and Cline. Covers install, real-world tests, and honest recommendations.

Fresh content:

Build a Self-Hosted RAG Pipeline on Linux: Chat with Your Documentation

Build a private RAG pipeline on Linux using Ollama, ChromaDB, and Python to chat with your own documentation, wikis, and knowledge bases without any cloud dependencies.

Build a Self-Hosted RAG Pipeline on Linux: Chat with Your Documentation Build a private RAG pipeline on Linux using Ollama, ChromaDB, and Python to chat with your own documentation, wikis, and knowledge bases without any cloud dependencies.

Read more:

LoRA Fine-Tuning on Linux: Customize LLMs with Your Own Data

Fine-tune LLMs with LoRA and QLoRA on Linux. Covers data preparation, training configuration, GPU requirements, evaluation, GGUF export, and Ollama deployment.

LoRA Fine-Tuning on Linux: Customize LLMs with Your Own Data Fine-tune LLMs with LoRA and QLoRA on Linux. Covers data preparation, training configuration, GPU requirements, evaluation, GGUF export, and Ollama deployment.

New article:

Multi-GPU LLM Inference on Linux: Setup, Load Balancing, and Scaling

Configure multi-GPU LLM inference on Linux with Ollama and vLLM, including tensor parallelism, load balancing across GPUs, NUMA optimization, and scaling strategies for production.

Multi-GPU LLM Inference on Linux: Setup, Load Balancing, and Scaling Configure multi-GPU LLM inference on Linux with Ollama and vLLM, including tensor parallelism, load balancing across GPUs, NUMA optimization, and scaling strategies for production.

Fresh content:

vLLM on Linux: Production Deployment Guide for High-Throughput Inference

Deploy vLLM on Linux for production LLM inference. Covers installation, API server config, tensor parallelism, quantization, monitoring, and load balancing.

vLLM on Linux: Production Deployment Guide for High-Throughput Inference Deploy vLLM on Linux for production LLM inference. Covers installation, API server config, tensor parallelism, quantization, monitoring, and load balancing.

Read more:

Power Consumption: Running LLMs 24/7 on Linux — Real Electricity Costs

Real-world power measurements and electricity costs for running LLMs on Linux 24/7. Covers GPU monitoring, cost calculations, self-hosted vs. cloud pricing, and power reduction strategies.

Power Consumption: Running LLMs 24/7 on Linux — Real Electricity Costs Real-world power measurements and electricity costs for running LLMs on Linux 24/7. Covers GPU monitoring, cost calculations, self-hosted vs. cloud pricing, and power reduction strategies.

New article:

Ollama on Proxmox: GPU Passthrough for LXC and VM AI Workloads

Configure NVIDIA GPU passthrough on Proxmox for Ollama AI workloads in both LXC containers and VMs, with IOMMU setup, driver configuration, and production deployment tips.

Ollama on Proxmox: GPU Passthrough for LXC and VM AI Workloads Configure NVIDIA GPU passthrough on Proxmox for Ollama AI workloads in both LXC containers and VMs, with IOMMU setup, driver configuration, and production deployment tips.

Fresh content:

Ollama on RHEL 9 and Rocky Linux: Enterprise Setup and SELinux Guide

Deploy Ollama on RHEL 9 and Rocky Linux with proper SELinux policies, firewalld rules, NVIDIA drivers, Podman support, and enterprise security hardening.

Ollama on RHEL 9 and Rocky Linux: Enterprise Setup and SELinux Guide Deploy Ollama on RHEL 9 and Rocky Linux with proper SELinux policies, firewalld rules, NVIDIA drivers, Podman support, and enterprise security hardening.