Skip to content
  • Home
  • AI
  • Programming
  • Game Development
  • Linux
  • About
  • rss

AI

  • 2026-05-24 · 10 min read · linux

    How to Limit GPU Power and Clock Speeds for AI Inference with a Dockerised Controller

    Running multiple GPUs for local AI inference at stock power settings is wasteful. Consumer cards like the RTX 3090 draw 350W by default, but AI inference workloads are typically memory-bandwidth

  • 2026-05-20 · 6 min read · AI

    How to cool passive NVIDIA GPUs (Tesla V100, P40) with a Dockerised Fan Controller

    The NVIDIA Tesla V100 and Tesla P40 are passively cooled cards, designed for data centre chassis with high-volume front-to-back airflow. Used in a desktop workstation or a home server they

  • 2026-05-20 · 4 min read · AI

    How to install drivers for NVIDIA Tesla V100 on Fedora 44 Server Edition for AI Inference

    The NVIDIA Tesla V100 has become a surprisingly attractive GPU for local LLM inference, thanks to its end-of-life status causing a flood of cheap used cards on the market. This

  • 2025-07-07 · 1 min read · AI

    How to run ComfyUI on an NVIDIA 5090 GPU

    How to fix CUDA errors when running ComfyUI on an NVIDIA RTX 5090 - use nightly PyTorch builds with CUDA 12.8 Blackwell support.

1 / 1
  • github
© 2026 Grosan Flaviu Gheorghe