Log_props output in TRT-LLM #11009
Closed
Log_props output in TRT-LLM #11009
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Signed-off-by: Onur Yilmaz <[email protected]>
Signed-off-by: Onur Yilmaz <[email protected]>
Signed-off-by: Onur Yilmaz <[email protected]>
athitten
reviewed
Oct 24, 2024
athitten
reviewed
Oct 24, 2024
|
@athitten If this PR works for you, I'll do some cleanup and start the CI. |
Signed-off-by: Onur Yilmaz <[email protected]>
@oyilmaz-nvidia sorry I dint get a chance to test it out yet. I will test it tomorrow. But the PR looks good otherwise. Thank you! |
athitten
approved these changes
Oct 25, 2024
There was a problem hiding this comment.
Tested it locally and it works, although the logProbs of the input tokens are 0.0 and logProbs of output tokens are as expected. It's probably some flag or setting on TRTLLM side to get logProbs of input tokens as well.
Thank you @oyilmaz-nvidia
|
Closing this since it'll be included here: #11233 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
What does this PR do ?
Adds the functionality to return log_props from TRT-LLM using PyTriton.