Skip to content

add bf16_int8 support for invokeLayerLLaMA API#470

Open
miaojinc wants to merge 1 commit intointel:mainfrom
miaojinc:main
Open

add bf16_int8 support for invokeLayerLLaMA API#470
miaojinc wants to merge 1 commit intointel:mainfrom
miaojinc:main

Conversation

@miaojinc
Copy link
Contributor

invokeLayerLLaMA API enhancement:

  1. Add bf16_int8 dtype support
  2. Add kvcache dtype argument
  3. Add Rope type argument

Signed-off-by: Jincheng Miao <jincheng.miao@intel.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant