Add support for stop words in TRTLLM #2678
Merged
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
# Conflicts: # backends/trtllm/lib/backend.cpp
Narsil
force-pushed
the
trtllm-stop-words
branch
from
9cee00e to
84f14a1
Compare
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Outdated suggestions cannot be applied.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.
[MERGE AFTER #2357]
This PR attempts to read the
eos_token_idsingeneration_config.json(if present) and creates a list (std::listrequired by trtllm) to cache those value.The list is then forwarded to TRTLLM's executor during request submission.
Known issues:
stop_sequencesare not yet supported