Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

initial_prompt for tensorrt backend #62

Open
draganjovanovich opened this issue May 21, 2024 · 1 comment
Open

initial_prompt for tensorrt backend #62

draganjovanovich opened this issue May 21, 2024 · 1 comment

Comments

@draganjovanovich
Copy link

Hi,

Can someone point parts of code that needs to be updated so initial_prompts can be used with tensorrt backend,
and if there are some limitations why it can't be done?

Thanks.
@mlecauchois
Copy link

By default in TRTBuilderConfig the max_input_len is equal to 4 which are the default prefix tokens without initial prompt. This param should be increased for prompts.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
2 participants
@draganjovanovich @mlecauchois