A team is optimizing a text-generation model where the computational cost is dominated by the self-attention mechanism during autoregressive decoding. They need to decide between two potential upgrades:
- Upgrade A: Doubling the number of layers in the model while keeping the maximum sequence length the same.
- Upgrade B: Doubling the maximum sequence length the model can handle while keeping the number of layers the same.
Assuming the model generates a sequence that fills its m
0
1
Tags
Ch.5 Inference - Foundations of Large Language Models
Foundations of Large Language Models
Foundations of Large Language Models Course
Computing Sciences
Application in Bloom's Taxonomy
Cognitive Psychology
Psychology
Social Science
Empirical Science
Science
Related
A team is optimizing a text-generation model where the computational cost is dominated by the self-attention mechanism during autoregressive decoding. They need to decide between two potential upgrades:
- Upgrade A: Doubling the number of layers in the model while keeping the maximum sequence length the same.
- Upgrade B: Doubling the maximum sequence length the model can handle while keeping the number of layers the same.
Assuming the model generates a sequence that fills its m
Derivation of Quadratic Complexity in Autoregressive Attention
Performance Bottleneck in a Generative Model
Vector Products per Self-Attention Step