Skip to content

draft pr about non-streaming output - #95

Open
BasicCoder wants to merge 2 commits into
triton-inference-server:mainfrom
BasicCoder:bc_draft_pr
Open

draft pr about non-streaming output #95
BasicCoder wants to merge 2 commits into
triton-inference-server:mainfrom
BasicCoder:bc_draft_pr

Conversation

@BasicCoder

Copy link
Copy Markdown

Try to get a valid output of the model, i.e. do not include the input of the model in the case of non-streaming

@Columpio

Copy link
Copy Markdown

@BasicCoder just pass exclude_input_in_output:True to tensorrt_llm/config.pbtxt.

Still you can transform this PR into making the above option default as many people struggle with it being disabled by default.

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.

2 participants