[LLM] sampling_params should be setup only if end_id is None and tokenizer is not None #2573
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
mfuntowicz
changed the title
|
Nice catch! Thanks for the contribution. |
|
Hi @mfuntowicz thanks for your contribution to TRT-LLM. We've merged your changes into our internal branch for the coming 0.16 release. |
|
Close it since this MR's changes have been upstreamed. |
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Outdated suggestions cannot be applied.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.
In the current version of the LLM API code, calling
generatewith a prefilledsampling_paramswould cause a potential undefined behaviour if notokenizeris defined on theLLMinstance.This is because the sampling_params should only be setup in the case
end_id == None and self.tokenizer != None. Otherwise we are at risk.This PR aims to solve this.