transformers
Fix VoxtralRealtime rejecting non-static cache implementations
#48082

Merged

Fix VoxtralRealtime rejecting non-static cache implementations #48082

zucchini-nlp merged 7 commits into huggingface:main from jiqing-feng:fix-voxtral-realtime-dynamic-cache

Fix VoxtralRealtime rejecting non-static cache implementations

46bfeeb1

Drop the offloaded cache from the new generation test

00af54e9

jiqing-feng marked this pull request as ready for review 82 days ago

github-actions requested a review from

ArthurZucker 82 days ago

github-actions requested a review from

Rocketknight1 82 days ago

Merge branch 'main' into fix-voxtral-realtime-dynamic-cache

f1f16e87

Merge branch 'main' into fix-voxtral-realtime-dynamic-cache

5e15b8cf

Merge branch 'main' into fix-voxtral-realtime-dynamic-cache

956bc162

zucchini-nlp approved these changes on 2026-09-01

Merge branch 'main' into fix-voxtral-realtime-dynamic-cache

e48dd769

Address review: mark generate test and rely on generic quant cache skip

38f8a323

zucchini-nlp approved these changes on 2026-09-02

zucchini-nlp enabled auto-merge 68 days ago

zucchini-nlp merged 58d5a2b7 into main 68 days ago

Reviewers

zucchini-nlp

ArthurZucker

Rocketknight1

Assignees

No one assigned

Labels

None yet

Milestone

No milestone