Note
This patch release includes important bug fixes to the function definition of Attention-23 under the Group Query Attention mode and to the reference implementation of RotaryEmbedding-23.
All changes
- Avoid unnecessary re-generating of proto files (#7253) in #7306
- Require ml_dtypes>=0.5.0 (#7254) in #7307
- Cherry pick four attention PRs in #7315
- Update rotary_embedding reference implementation and tests (#7304, #7316) in #7313
- Override
__repr__for some proto classes (#7259) in #7314 - Update version number to 1.19.1rc1 in #7322
- add check for rc-candidates (Update create_release.yml) (#7261) in #7323
- Implement repr methods for Model/Graph/Function (#7320) in #7325