Qualcomm AI Engine Direct - Suport batch prefill mode for llama3.2#6983

Merged

cccclai merged 8 commits intopytorch:mainfrom

CodeLinaro:dev1/chunit/bert_mode

Dec 3, 2024

Commits on Dec 1, 2024

Qualcomm AI Engine Direct - Suport bert mode for llama3.2
Joey Tsai
committed
Rebase and minor fix
Joey Tsai
committed
Change bert to batch prefill
Joey Tsai
committed
Fix compile error
Joey Tsai
committed
Fix lint
Joey Tsai
committed
Add one line in the end of CmakeList
Joey Tsai
committed
Remove trailing line of CmakeList
Joey Tsai
committed
Move noqa to correct line number
Joey Tsai
committed