text-generation-inference
Add chunked attn for L4
#3162
Open
Overview
Commits
5
Changes
View On GitHub
Commits
  • add fix
    mht-sharma committed 259 days ago
  • reverse flash causal change
    mht-sharma committed 259 days ago
  • support cuda graphs
    mht-sharma committed 258 days ago
  • fix bt
    mht-sharma committed 258 days ago
  • force attn to flashdecoding
    mht-sharma committed 258 days ago
FAQ Terms Privacy Refunds Impressum
Loading