Concept dictionary
Inference
Inference is the process of running a trained model on an input to produce a prediction, classification, generation, or other output.
- Review state
- Needs review
- Freshness
- Current
- Version
- 2
Also called
- Inference
- Model Inference
Remember it this wayTraining changes the model; inference uses it.
In plain language
Training is when the model's learned values are adjusted. Inference is when the trained model is used, such as when it answers a prompt or analyzes a new image.
Why it matters
Inference determines run-time speed, cost, hardware needs, privacy exposure, and how a model is integrated into a real workflow.
Example
When a user submits a prompt and the model generates a response, the model is performing inference.
Common misconception
Ordinary inference does not necessarily update the model's weights or make it learn permanently from each request.
Related terms
Sources
- Google for Developers, Machine Learning Glossary: Inferencetechnical definition of applying a trained model to unlabeled examples to make predictions.
- NIST, Adversarial Machine Learning: A Taxonomy and Terminology of Attacks and Mitigations (NIST AI 100-2 E2025)lifecycle terminology distinguishing training and inference stages.
Learn more
- Connect run-time behavior to [[latency|Latency]] and [[compute|Compute]].