parallelisation
A workflow that runs several model calls at once, either on separate parts of a task (sectioning) or on the same task for a vote.
In more detail
Sectioning speeds up independent subtasks; voting trades cost for confidence, as in self-consistency. Your code merges the results.
Related terms
- workflow (LLM) — A system in which your code fixes the sequence of model calls and tools, as opposed to an agent that chooses its own steps.
- self-consistency — Sampling several reasoning paths for the same question and taking the most common final answer.
Taught in
- Reasoning Techniques — AI Engineering: LLM Apps, RAG & Agents
- Workflows Before Agents — AI Engineering: LLM Apps, RAG & Agents