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

2 terms in Serving

Expert parallelismServing

MoE-specific technique: instead of splitting every layer, the experts (conditional sub-networks) are distributed across GPUs. A token only invokes the active experts, so VRAM is used more efficiently than with tensor parallelism.

Tensor parallelismServing

Serving technique that splits each matrix (tensor) of a model across multiple GPUs: each card computes a part of the same layer and the results are recomposed. Used when a single layer doesn't fit on one GPU, e.g. for large MoE models.