Topics Practice Study

Zenaique

Personalized AI interview prep. Structured questions across every GenAI sub-discipline. Practice, score, master.

Practice

Topics
Practice
Challenges
Dashboard

Browse

Formats
Roles
Companies
Top questions

Product

Pricing
Sign in

© 2026 Zenaique

Topics/Attention Mechanism/Autoregressive Decoding

Autoregressive Decoding

Subtopic8 questions

Questions tagged with Autoregressive Decoding — part of Attention Mechanism.

Premium questions for this topic

Sort

Questions

Walk through KV-cache updates when speculative decoding rejects some draft tokens
Short AnswerMedium
During decode, why is only Q computed for the new token while full K and V come from cache?
Multiple ChoiceEasy
Why does a small FT dramatically improve strict JSON output?
Short AnswerMedium
What exactly does the KV cache store and what computational redundancy does it eliminate?
Short AnswerMedium
Why does autoregressive generation use a KV cache?
Short AnswerMedium
PremiumWhat does the KV…
Multiple ChoiceMedium
In LLM serving, what is the primary driver of end to end latency for a generation request?
Multiple ChoiceMedium
What is the KV cache in transformer inference?
FlashcardEasy

Study answers

Read the beginner answer for every question in this topic.

Study beginner answers

Master this topic

Daily practice mixes topics. Topic specific drill is a Pro feature.

Inflection Ai Lepton Ai

Cloudflare Snap

Autodesk Modal Labs

Mphasis Together Ai

Elevenlabs Phonepe