thinQmaster Virtual testing partner Adaptive practice exams that find your weak spots and drill them. Every answer explained. From $69
Enroll

thinQmaster

Find your exam

Five questions free, before you decide.

Step 1 · choose a vendor

In one of our camps? Your practice exams come with the tuition — they are on your study page already.

AI & Machine Learning · Intermediate

Autoregressive Generation

Producing output one token at a time, with each new token conditioned on all previously generated tokens.

Definition

LLMs generate by repeatedly predicting a next-token distribution, selecting a token by a decoding strategy, appending it and repeating until a stop condition. This sequential decode phase dominates latency for long outputs.

Exam tip

Output length drives latency because tokens are generated one at a time.

Related terms