Skip to content

Refactor turbomind attention by precomputing rotary embed #6131

Refactor turbomind attention by precomputing rotary embed

Refactor turbomind attention by precomputing rotary embed #6131

Triggered via pull request December 3, 2024 12:58
@irexycirexyc
synchronize #2801
irexyc:rope
Status Success
Total duration 5m 1s
Artifacts

lint.yml

on: pull_request
Fit to window
Zoom out
Zoom in