Zenaique
Topics
Practice
Browse
Reference
Challenges
Pricing
Search…
⌘K
Topics
/
Inference Optimization
/
Memory Bound
Memory Bound
Subtopic
4 questions
Questions tagged with Memory Bound — part of Inference Optimization.
Format
Difficulty
Role
Experience
Companies
Sort
Newest
Quality
Difficulty ↑
Difficulty ↓
Questions
Each decode step loads ___ from HBM, regardless of how many tokens have already been generated
Fill in Blank
Easy
·
Qual 4.0
FLOPs vs FLOP/s: fill in the counts versus rate distinction.
Fill in Blank
Easy
·
Qual 4.0
What is the arithmetic intensity of an LLM decode step and why is it close to 1?
Short Answer
Hard
·
Qual 4.0
NVIDIA
Why is standard attention memory bandwidth bound rather than compute bound on modern GPUs?
Multiple Choice
Hard
·
Qual 4.0