gemma.cpp

What's Changed

• Refactor Gemma ctor and improve pool NUMA support by @copybara-service in https://github.com/google/gemma.cpp/pull/520
• Fix the prompt wrapping of gemma3-1b by @ufownl in https://github.com/google/gemma.cpp/pull/523
• Add note on attention length and SFP by @copybara-service in https://github.com/google/gemma.cpp/pull/521
• Add support for a secondary EOS token by @copybar...

• Support for PaliGemma 2 and Gemma 3.
• Major update to MatMul and MatMul-using operations; significant performance increases in multiple parts of the codebase.
• Codebase simplifications and refactors in many areas.
• Bugfixes

What's Changed

• Add more ops: Sigmoid, (Two)MatVecAdd. Faster TwoMatVec. by @veluca93 in https://github.com/google/gemma.cpp/pull/129
• Improve weight handling...

• MQA implementation
• Ops refactorings and optimizations
• Bugfixes
• Model exporting script (util/convert_weights.py)

Important Note: With the MQA implementation, older 2B model artifacts need to be updated. Please re-download weights from Kaggle and ensure you have the latest version (-mqa or version 3).

What's Changed

• Clean up docs for developers by @austinvhuang in https:/...

• Refactor library interfaces
• Fixes to enable android and windows builds + general improvements to builds
• Bazel builds
• CI automation
• Allow either HF or Kaggle (vs Kaggle only) for artifact downloads
• Many small fixes and quality-of-life improvements from initial 0.1.0 release

What's Changed

• Dev -> Main sync by @austinvhuang in https://github.com/google/gemma.cpp/pull/24
• U...

Initial release.