[Core] Add support for draft models for speculative decoding#535
Draft
TJ5 wants to merge 9 commits intoome-projects:mainfrom
Draft
[Core] Add support for draft models for speculative decoding#535TJ5 wants to merge 9 commits intoome-projects:mainfrom
TJ5 wants to merge 9 commits intoome-projects:mainfrom
Conversation
TJ5
requested review from
CatherineSue,
XinyueZhang369,
YouNeedCryDear,
beiguo218,
pallasathena92 and
slin1237
as code owners
Contributor
|
Warning You have reached your daily quota limit. Please wait up to 24 hours and I will start processing your requests again! |
github-actions
Bot
added
documentation
TJ5
changed the title
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 this PR does
Updates inference service to have a draft model as part of the spec, for use in speculative decoding. Configurations for use of the feature with nvidia/gpt-oss-120b-eagle3-long-context are added.
Why we need it
Speculative decoding increases inference speed, which is useful for long running agentic tasks. OME previously did not support deploying draft models, required for speculative decoding.
How to test
go test ./pkg/runtimeselector/...Checklist
make testpasses locally