AI
-
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
-
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
-
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
-
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.