Skip to content

llama: enable tensor split for bailingmoe3 + nemotron_h_moe - #5

Open
assistmeister wants to merge 3 commits into
mxxm-t:masterfrom
assistmeister:tp-bailingmoe3
Open

llama: enable tensor split for bailingmoe3 + nemotron_h_moe#5
assistmeister wants to merge 3 commits into
mxxm-t:masterfrom
assistmeister:tp-bailingmoe3

llama: guard split granularity against zeroed attention hparams

2fb3f3d
Select commit
Loading
Failed to load commit list.
Sign in for the full log view