In a controlled GPT-2 fine-tuning benchmark, Flash Attention consumed the least GPU energy (1.07 MJ), followed closely by LSH Attention and Multi-Head Latent Attention.
Gqa: Training generalized multi-query transformer models from multi-head checkpoints
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Attentions Under the Microscope: A Comparative Study of Resource Utilization for Variants of Self-Attention
In a controlled GPT-2 fine-tuning benchmark, Flash Attention consumed the least GPU energy (1.07 MJ), followed closely by LSH Attention and Multi-Head Latent Attention.