Skip to content

Refactor turbomind attention by precomputing rotary embed #3107

Refactor turbomind attention by precomputing rotary embed

Refactor turbomind attention by precomputing rotary embed #3107

Triggered via pull request December 2, 2024 13:06
@irexycirexyc
synchronize #2801
irexyc:rope
Status Success
Total duration 12m 38s
Artifacts

unit-test.yml

on: pull_request
Fit to window
Zoom out
Zoom in