enable chunked prefill with speculative decoding#537
Merged
Conversation
michaelfeil
approved these changes
Jan 29, 2026
Contributor
michaelfeil
left a comment
michaelfeil
left a comment
There was a problem hiding this comment.
approve penign changes
...anker-classification-tensorrt/Briton-google-gemma-3-27b-it-speculative-lookahead/config.yaml
Outdated
Show resolved
Hide resolved
TRT-LLM issue #5451 has been resolved, allowing chunked prefill to work alongside speculative decoding. Removes the restriction that disabled chunked prefill when speculative decoding was enabled. Also increases max_seq_len cap from 32768 to 262144 for speculative decoding builds.
thomasj02
force-pushed
the
tjohnson/enable-chunked-prefill-with-speculative-decoding
branch
from
a231566 to
5ee6de8
Compare
thomasj02
deleted the
tjohnson/enable-chunked-prefill-with-speculative-decoding
branch
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
basetenlabs/basetenwhich removes theBRITON_ALLOW_SPEC_DEC_CHUNKED_PREFILLenv var checkChanges
generate_templates.pythat setenable_chunked_context = Falsefor speculative decoding