Skip to content

[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
mainfrom
serge/fix/itf-1c12a6ad471e-470a612b
Open

[serge] Fix 10 integration tests for model gemma3 failing with output_mismatch (list output differs (8), other (2))#47006
sergereview[bot] wants to merge 2 commits into
mainfrom
serge/fix/itf-1c12a6ad471e-470a612b

Conversation

@sergereview

@sergereview sergereview Bot commented Jul 1, 2026

Copy link
Copy Markdown

CI

Original CI failure

  • Failure group: 1/1: 10 integration tests for model gemma3failing 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_default failures in the Gemma3 integration group.

Root cause: the code path in generate() was unconditionally clearing cache_implementation="hybrid" even when the caller explicitly passed cache_implementation="hybrid". The comment says the goal is to clear only the Hub default, not an explicit user argument.

Patch: only clear "hybrid" when cache_implementation was not supplied in generate() kwargs. This restores the expected behavior that explicit cache_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

…put_mismatch` (list output differs (8), other (2))
@HuggingFaceDocBuilderDev

Copy link
Copy Markdown

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))
@github-actions

github-actions Bot commented Jul 2, 2026

Copy link
Copy Markdown
Contributor

CI recap

Dashboard: View test results in Grafana
Latest run: 28559765420:1
Result: success | Jobs: 14 | Tests: 69,253 | Failures: 0 | Duration: 18h 10m

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant