AI inference glossary
Software

CUDA

Also known as NVIDIA CUDA

In plain English

CUDA is NVIDIA’s software toolbox for making programs run on its GPUs.

Technical definition

CUDA is NVIDIA’s GPU computing platform, programming model, compiler toolchain, and library ecosystem.

Engineering details

LLM engines use CUDA kernels and libraries for matrix multiplication, attention, collectives, graph capture, memory management, and custom fused operations. Container, driver, CUDA, and GPU architecture versions must be compatible.

Why it matters

Serving performance depends on the software above the silicon. New kernels, CUDA Graph usage, compiler specialization, and library releases can move the benchmark curve without changing the GPU.

How to read it in InferenceX

InferenceX recipes pin container images and therefore a concrete CUDA stack. Historical comparisons can isolate the effect of an engine image bump on otherwise identical hardware and configuration.