perf(qwen35): add SpecLA factor-capture speculative decoding - #606
Draft
Graffioh wants to merge 3 commits into
Draft
perf(qwen35): add SpecLA factor-capture speculative decoding#606Graffioh wants to merge 3 commits into
Graffioh wants to merge 3 commits into
Conversation
Graffioh
force-pushed
the
codex/qwen35-specla-current-main
branch
from
August 13, 2026 10:55
27417ca to
5f38668
Compare
Contributor
Author
|
@cubic-dev-ai review this PR |
Contributor
@Graffioh I have started the AI code review. It will take a few minutes to complete. |
![cubic-dev-ai[bot]](https://avatars.githubusercontent.com/in/1082092?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
1 issue found across 33 files
Prompt for AI agents (unresolved issues)
Check if these issues are valid — if so, understand the root cause of each and fix them. If appropriate, use sub-agents to investigate and fix each issue separately.
<file name="server/src/qwen35/qwen35_dflash_target.cpp">
<violation number="1" location="server/src/qwen35/qwen35_dflash_target.cpp:609">
P2: The SpecLA bank-rotation / `specla_compact_fused` / `specla_flush_raw_fused` logic is copied nearly verbatim between this file and `server/test/test_dflash.cpp`. `rollback_to_tree` (walked_sibling compaction + `current_bank`/`old_pending_bank` rotation + `pending_count` update), `finish_speculative_state` (bank selection via `specla_pending_bank` + `specla_flush_raw_fused`), and `rollback_to_specla` (bank toggle + count) each have a hand-maintained mirror in the bench harness. These are the two most state-sensitive routines in the PR; any divergence between the production target and the harness (e.g. the `ne` bounds, channel mapping, or bank-toggle logic) silently changes acceptance behavior. Pull the shared commit/flush helpers into a common function (e.g. in `specla_commit_cuda.h/.cu`) and have both call sites invoke it.</violation>
</file>
Reply with feedback, questions, or to request a fix.
Re-trigger cubic
Graffioh
force-pushed
the
codex/qwen35-specla-current-main
branch
from
August 15, 2026 07:11
5f38668 to
e7dc8f0
Compare
Graffioh
force-pushed
the
codex/qwen35-specla-current-main
branch
from
August 15, 2026 07:16
e7dc8f0 to
c775f9e
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
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.
Current gain over
mainQwen3.6-27B Q4_K_M target, Q8_0 DFlash draft, DDTree budget 22, top-k 4,
tau=6, ten HumanEval-style prompts, and 128 generated tokens:mainSpecLA gain over current
main: +8.2%.