inferencing

American  

[in-fer-uhns-ing] / ˈɪn fər əns ɪŋ /

noun

1. the process and practice of inferring or making inferences.

2. the process through which a deep learning model generates output in response to input.

---

inferencing British  

/ ˈɪnfərənsɪŋ /

noun

1. psycholinguistics the practice of inferring the meaning of an unfamiliar word or expression from the meaning of familiar words occurring with it in a context together with one's knowledge of or beliefs about the world

---

Example Sentences

The chips are built for demanding AI workloads, including high-volume AI inferencing, according to Google.

From MarketWatch

Inferencing refers to the process of running AI models.

From MarketWatch

Training is a sunk cost, Singh noted, because although it is important to train models to improve them, inferencing is related to the monetization of the AI models.

From MarketWatch

Su is also hoping to capitalize on an inflection point in AI—many executives in the chips industry, including Nvidia chief Jensen Huang, expect demand to shift from clusters designed to assist in training large language models to what’s known as inferencing, or the billions of computations required to run those models and allow them to respond to user queries.

From The Wall Street Journal

Inferencing doesn’t require chips with as much computing muscle as training does.

From The Wall Street Journal