[Fix] Drop the duplicated DSpark draft sample_block call - #36934
Merged
Merged
Conversation
hnyls2002
requested review from
Qiaolin-Yu,
Ying1123 and
merrymercy
as code owners
August 29, 2026 00:33
Collaborator
Author
|
/rerun-test registered/core/test_basic_sanity_dspark.py registered/spec/dspark/test_dspark_kernel_parity.py registered/spec/dspark/test_dspark_stacked_ctx_kv_parity.py |
Contributor
|
Results for 🚀 🚀 |
Collaborator
Author
|
/tag-and-rerun-ci |
saturn-acc
pushed a commit
to saturn-acc/sglang
that referenced
this pull request
Aug 31, 2026
nzr-niu
pushed a commit
to nzr-niu/sglang
that referenced
this pull request
Sep 1, 2026
This was referenced Sep 10, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
DsparkDraftSampler.__call__runssample_blocktwice: the call added inside theif draft_tokens is None:block (#33561) plus the original trailing one, which overwrites it.self.outcame from the second call andself.corrected_outfrom the first, so the emitted draft tokens and the corrected logits were drawn from two separate passes.Note this activates the fused greedy fast path, whose result was previously computed and then discarded.
CI States
Latest PR Test (Base): 🚫 Run #33223878538
Latest PR Test (Extra): ❌ Run #33223878487
Latest PR Test (AMD ROCm 7.2): 🚫 Run #33223878558