🍥

记录并分享日常

Tags

7 pages

CUDA

MinerU not using the GPU? Replace CPU PyTorch with the CUDA build to enable RTX 4060

How to choose the five MinerU 3.4 modes: pipeline, hybrid-engine, vlm-engine, hybrid-http-client, and vlm-http-client

Ubuntu 26.04 LTS GPU and Hardware Updates: CUDA, ROCm, DPC++, and More Platform Changes

What Is NVIDIA nvbandwidth: How to Use This GPU Bandwidth Testing Tool

llama.cpp GPU Benchmark: CUDA vs ROCm vs Vulkan Scoreboard and pp512/tg128 Explained

What the Common GPU Inference Benchmark Metrics Actually Mean: FA, pp512, tg128, and Q4_0

Ollama Multi-GPU Guide: VRAM Pooling, GPU Selection, and Performance Limits