Skip to content

Refactor turbomind attention by precomputing rotary embed #6125

Refactor turbomind attention by precomputing rotary embed

Refactor turbomind attention by precomputing rotary embed #6125

Triggered via pull request December 3, 2024 07:30
@irexycirexyc
synchronize #2801
irexyc:rope
Status Success
Total duration 3m 55s
Artifacts

lint.yml

on: pull_request
Fit to window
Zoom out
Zoom in