transformers
c4e20698 - Fix Cache.max_cache_len max value for Hybrid models (#39737)

Commit

305 days ago

Fix Cache.max_cache_len max value for Hybrid models (#39737) * fix gemma * fix min * fix quant init issue * fix gemma 3n * skip quant cache test * fix modular * new test for Gemma * include cyril change --------- Co-authored-by: Cyril Vallez <cyril.vallez@gmail.com>

References

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

#59 - Fix attention mask handling in EoMT-DINOv3 converter

#62 - Add initial DEIMv2 model implementation

#65 - Fix RTDetrV2 sine position embedding ordering

#44375 - Add RF-DETR

#71 - Use Mask2Former ignore_value in mask matching and losses

#44385 - Fix make check-repo

#45082 - [VidEoMT] Update conversion script

#45110 - Add SAM 3.1

Author

manueldeprada

Parents

075dbbce

transformers c4e20698 - Fix Cache.max_cache_len max value for Hybrid models (#39737)

transformers
c4e20698 - Fix Cache.max_cache_len max value for Hybrid models (#39737)