Skip to content

llama : use F32 precision in GLM4 attention and no FA (#9130) #1978

llama : use F32 precision in GLM4 attention and no FA (#9130)

llama : use F32 precision in GLM4 attention and no FA (#9130) #1978

Triggered via push August 23, 2024 07:30
Status Success
Total duration 34m 50s
Artifacts
check-requirements
2m 20s
check-requirements
Fit to window
Zoom out
Zoom in