[Spec] Relay next_draft_input via GenerationBatchResult; unify scheduler install#24862
Open
hnyls2002 wants to merge 10 commits into
Open
[Spec] Relay next_draft_input via GenerationBatchResult; unify scheduler install#24862hnyls2002 wants to merge 10 commits into
hnyls2002 wants to merge 10 commits into
Conversation
hnyls2002
requested review from
Qiaolin-Yu,
Ying1123,
merrymercy and
xiezhq-hermann
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! |
2 tasks
…nput; executor installs
…GenerationBatchResult
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Stacks on #24860. Unifies the cross-iteration
spec_infoinstall across V1, V2, and Frozen KV MTP workers viaGenerationBatchResult.next_draft_input.batch.spec_info = next_draft_inputdirectly; V2 has its own scheduler-side install gated byis_spec_v2; Frozen does worker-side install. 3 different patterns.next_draft_inputviaGenerationBatchResult. Scheduler installs frombatch_result.next_draft_inputin one place.Other cleanups (move install of
batch.spec_infofromprepare_*methods to the caller, drop deadcheck_forward_draft_extend_after_decode, rename V2sample→verify_v2, lift V1 idle-extend swap to caller).Test plan