gemma.cpp/gemma
Jan Wassenberg 794a21a4e6 Major refactor to de-templatize gemma-inl and weights
This replaces per-weight instantiations of all code with only per-MatMul/norm.
Reduces binary size by 133KiB.

WeightsOwner is no longer required for type erasing, hence it is replaced with ModelWeightsPtrs.
Also remove unused EmbedToken, replaced with EmbedMMToken.

PiperOrigin-RevId: 766497657
2025-06-02 23:01:35 -07:00
..
bindings Replace RowVectorBatch with MatStorageT 2025-05-12 09:16:12 -07:00
evals Add MMLU eval to github 2024-05-20 10:20:53 -07:00
activations.h Major refactor to de-templatize gemma-inl and weights 2025-06-02 23:01:35 -07:00
common.cc Huge refactor of weight handling and model loading. 2025-05-06 04:44:21 -07:00
common.h Remove backprop/ 2025-05-28 07:01:17 -07:00
configs.cc Internal change. 2025-05-30 09:18:44 -07:00
configs.h 1.16x decode speedup: remove last MatVec in Attention 2025-06-02 09:40:29 -07:00
configs_test.cc Minor: rename compression/shared -> types.h 2025-05-13 06:53:21 -07:00
gemma-inl.h Major refactor to de-templatize gemma-inl and weights 2025-06-02 23:01:35 -07:00
gemma.cc Major refactor to de-templatize gemma-inl and weights 2025-06-02 23:01:35 -07:00
gemma.h Major refactor to de-templatize gemma-inl and weights 2025-06-02 23:01:35 -07:00
gemma_args.h Cleanup: remove unused kCyclic, remove 2 suffix 2025-05-13 01:06:41 -07:00
kv_cache.cc Fix RowT issue and improve Griffin (currently still broken) 2025-05-19 07:02:10 -07:00
kv_cache.h Fix RowT issue and improve Griffin (currently still broken) 2025-05-19 07:02:10 -07:00
model_store.cc Major refactor to de-templatize gemma-inl and weights 2025-06-02 23:01:35 -07:00
model_store.h Remove backprop/ 2025-05-28 07:01:17 -07:00
run.cc Minor fixes for ViT 2025-05-20 22:27:10 +08:00
tensor_info.cc Major refactor to de-templatize gemma-inl and weights 2025-06-02 23:01:35 -07:00
tensor_info.h Minor: rename compression/shared -> types.h 2025-05-13 06:53:21 -07:00
tensor_info_test.cc Major refactor to de-templatize gemma-inl and weights 2025-06-02 23:01:35 -07:00
tokenizer.cc Huge refactor of weight handling and model loading. 2025-05-06 04:44:21 -07:00
tokenizer.h Remove backprop/ 2025-05-28 07:01:17 -07:00
weights.cc Major refactor to de-templatize gemma-inl and weights 2025-06-02 23:01:35 -07:00
weights.h Major refactor to de-templatize gemma-inl and weights 2025-06-02 23:01:35 -07:00