Flash-ABFT verifies an entire transformer attention layer with one fused checksum that covers softmax and all three matrix products, reporting 96-99% fault detection at under 5.3% area overhead.
An image is worth 16x16 words: Transformers for image recognition at scale,
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
unclear 1representative citing papers
citing papers explorer
-
Custom Algorithm-based Fault Tolerance for Attention Layers in Transformers
Flash-ABFT verifies an entire transformer attention layer with one fused checksum that covers softmax and all three matrix products, reporting 96-99% fault detection at under 5.3% area overhead.