gpus

Practical, Linux-first guide showing how the right hardware, not just FLOPs, cuts latency, cost, and power. Through three copy-paste case studies (CPU ONNX Runtime with NUMA/thread tuning, single-GPU PyTorch LoRA with 4/8-bit, and portable llama.cpp C++ inference), it gives install commands, monitoring tips (sensors, nvtop), repeatable benchmarks, and advice on topology, quantization, and clean environments.

A practical, Bash-first guide to building a private AI homelab on Linux: prepare OS and tools, use Docker or Podman, optionally enable GPU (NVIDIA with AMD/ROCm notes), run a local LLM via Ollama + Open WebUI and generate images with ComfyUI, or experiment in a Python venv. Includes hardening (firewall, services), monitoring, storage/backups, hardware sizing, and next steps like RAG, Compose scripting, scheduling, and benchmarking.