Skip to content

Should I use linear layers for the input and output of FlashAttention? #240

Should I use linear layers for the input and output of FlashAttention?

Should I use linear layers for the input and output of FlashAttention? #240

Triggered via issue July 21, 2024 09:26
Status Success
Total duration 29s
Artifacts

welcome.yml

on: issues
👋 Welcome
19s
👋 Welcome
Fit to window
Zoom out
Zoom in