transformers
Fix Cache.max_cache_len max value for Hybrid models
#39737

Merged

Fix Cache.max_cache_len max value for Hybrid models #39737

Cyrilvallez merged 10 commits into huggingface:main from manueldeprada:max-cache-len-fix

fix gemma

40c604ba

manueldeprada requested a review from

gante 173 days ago

ArthurZucker added for patch

fix min

d143de4e

fix quant init issue

404208a4

Merge branch 'main' of github.com:huggingface/transformers into max-c…

8aff7492

fix gemma 3n

ee1fe17c

Merge branch 'max-cache-len-fix' of https://github.com/manueldeprada/…

31b1bbef

skip quant cache test

82a2c5fc

fix modular

e4e6cc7b

manueldeprada commented on 2025-07-29

new test for Gemma

ffb2c618

manueldeprada commented on 2025-07-29

include cyril change

e3ca2a30

manueldeprada commented on 2025-07-29

Cyrilvallez approved these changes on 2025-07-29

Cyrilvallez merged c4e20698 into main 172 days ago

Reviewers

Cyrilvallez

gante

Assignees

No one assigned

Labels

for patch

Milestone

No milestone