test(tito): use FP8 Qwen3.6 checkpoint - #2791
Merged
Merged
Conversation
Switch the session verifier to the official Qwen3.6-35B-A3B-FP8 checkpoint while preserving its CUDA and ROCm lanes, four-GPU topology, speculative decoding, parsers, and TITO gates.
![claude[bot]](https://avatars.githubusercontent.com/in/1236702?s=60&v=4){kind=small}
There was a problem hiding this comment.
Claude Code Review
This repository is configured for manual code reviews. Comment @claude review for a one-time review, or @claude review always to subscribe this PR to a review on every future push.
Tip: disable this comment in your organization's Code Review settings.
|
✅ |
Contributor
|
@claude review always. |
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Run the Qwen3.6 TITO session verifier with the FP8 checkpoint.
Motivation
The Qwen3.6 session verifier currently loads the full-precision 35B checkpoint even though this CI surface validates TITO chat serialization and session reuse. The matching FP8 checkpoint keeps that validation target while avoiding the full-precision model artifact.
Before / After
test_qwen36.pychangesQwen/Qwen3.6-35B-A3BtoQwen/Qwen3.6-35B-A3B-FP8.ModelConfig.model_namechanges.Behavior Preservation
CONFIGkeeps the same topology, speculative decoding, parsers, cycles, and append-tool behavior.Verification
uvx pre-commit run --files tests/e2e/sglang/test_session_server_multi_role/test_qwen36.py: passed.tests.ci.file_run: resolved the file to CUDA suitestage-c-4-gpu-h200, runner labelsh200,4gpu, and a 1,800-second timeout.test_qwen36.pyGPU execution: pending; only this file will be dispatched after PR creation.Review Focus
ModelConfig.model_name: the FP8 checkpoint must preserve the tokenizer and chat-template behavior exercised by TITO.