[serge] Fix 10 integration tests for model gemma3 failing with output_mismatch (list output differs (8), other (2))#47006
Open
sergereview[bot] wants to merge 2 commits into
Open
Conversation
…put_mismatch` (list output differs (8), other (2))
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
…put_mismatch` (list output differs (8), other (2))
Contributor
CI recapDashboard: View test results in Grafana |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Original CI failure
1/1: 10 integration tests for modelgemma3failing withoutput_mismatch(list output differs (8), other (2))tests/models/gemma3/test_modeling_gemma3.py::Gemma3IntegrationTest::test_dynamic_sliding_window_is_default[multi-gpu] (output_mismatch, seen 7/7)Relates to #46998
Fixes the
test_dynamic_sliding_window_is_defaultfailures in the Gemma3 integration group.Root cause: the code path in
generate()was unconditionally clearingcache_implementation="hybrid"even when the caller explicitly passedcache_implementation="hybrid". The comment says the goal is to clear only the Hub default, not an explicit user argument.Patch: only clear
"hybrid"whencache_implementationwas not supplied ingenerate()kwargs. This restores the expected behavior that explicitcache_implementation="hybrid"uses the static sliding-window cache.Note: the remaining 8 text-output mismatches in the same group appear to be unrelated expected-value drifts and are not addressed by this library fix.
This change was produced automatically by serge from a CI failure report. The patch was generated by an LLM and applied by serge; review before merging.
serge
v0.1.0· model:moonshotai/Kimi-K2.7-Code· 27 LLM turns · 30 tool calls · 513.0s · 762898 in / 12583 out tokens