Papers
Communities
Events
Blog
Pricing
Search
Open menu
Home
Papers
2505.15080
Cited By
v1
v2 (latest)
SUS backprop: linear backpropagation algorithm for long inputs in transformers
21 May 2025
Sergey Pankov
Georges Harik
Re-assign community
ArXiv (abs)
PDF
HTML
Papers citing
"SUS backprop: linear backpropagation algorithm for long inputs in transformers"
1 / 1 papers shown
Title
Fast Transformer Decoding: One Write-Head is All You Need
Noam M. Shazeer
163
477
0
06 Nov 2019
1
