Skip to content

vela: add the 0.8B native response finishing and backbone execution on CUDA - #177

Open
MrDongsls wants to merge 18 commits into
InferMatrixLab:mainfrom
MrDongsls:model/vela2-native-executor
Open

MrDongsls wants to merge 18 commits into
InferMatrixLab:mainfrom
MrDongsls:model/vela2-native-executor

Commits

  1. Commits on Nov 10, 2026