fix(qwen35): size mixed concurrent target-step graphs - #622
Draft
Graffioh wants to merge 1 commit into
Draft
Conversation
Graffioh
force-pushed
the
codex/ar-prefill-latency
branch
2 times, most recently
from
August 18, 2026 10:42
4742333 to
812eabc
Compare
Graffioh
force-pushed
the
codex/ar-prefill-latency
branch
from
August 20, 2026 06:28
30c47a7 to
5b7d306
Compare
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Problem
The Qwen target-step builder always allocates a 16,384-node graph. That is large enough for eight independent recurrent segments, but the default C16 continuous-serving path can legally schedule eight packed prefills plus compact decode in one traversal.
That ninth recurrent segment builds 16,741 nodes and aborts during graph construction. This reproduces on
mainwith the normal continuous-decode scheduler; it is not caused by an experimental policy.Fix
The observed C16 schedule now receives an 18,432-node graph. Common shapes at or below eight recurrent segments retain the existing capacity.
Scope
This PR is now only the graph-sizing correctness fix. The prefill-first scheduling experiment was removed after warmed three-repeat gfx1151 screening showed only a 1-3% C16 TTFT gain, a C8 TTFT regression, and materially worse overlap ITL. The existing invariant that every normal decode plan covers the complete live cohort remains unchanged.
Validation
git diff --checkpassed.