Local AI Glossary

Terms and definitions of local artificial intelligence, open source models, and computing.

Sort terms by:Name (A-Z)Name (Z-A)Category

All categories Training Architectures Use cases Concepts Formats Hardware Model types Generative models Optimization Performance Serving Security Tools Techniques Technologies tecnologie

3 terms in tecnologie

CUDAtecnologie

Compute Unified Device Architecture: NVIDIA's GPU programming stack — libraries, compiler and runtime that run model inference on NVIDIA GPUs. It is the default backend for Ollama and llama.cpp on NVIDIA hardware: optimizations (Flash Attention, quantized kernels, FP4 formats) arrive on CUDA first.

RDNAtecnologie

Radeon DNA: AMD's consumer GPU architecture. RDNA 3 (RX 7000 series) and RDNA 4 (RX 9000 series) are the families officially supported by ROCm 7 on Linux for local AI, with Ollama and llama.cpp and no workarounds: the GPU targets are gfx1100 for RDNA 3 and gfx1200/gfx1201 for RDNA 4.

Vulkantecnologie

Khronos's cross-platform GPU programming API, born in gaming but now the open path for local AI: Ollama and llama.cpp support it natively on Windows, Linux and macOS (via MoltenVK), on NVIDIA, AMD and Intel with no proprietary drivers. Less optimized for inference than CUDA — usually 70-90% of the native path's speed — but it is the only stack that works on practically every card, and it is the maintained path for Intel Arc GPUs since IPEX-LLM was archived.