happyz
/
gemma.cpp
mirror of https://github.com/google/gemma.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
gemma.cpp/gemma
History
The gemma.cpp Authors 1f916b686b Adds: 
- GemmaContext class that exposes Gemma functionality
- C API that uses GemmaContext
- C# interop class in GemmaInterop.cs
- New END_OF_TURN_ID in tokenizer.h, useful when dealing with instruction-tuned prompts

PiperOrigin-RevId: 730754638
 		2025-02-25 01:00:02 -08:00
..
evals Add MMLU eval to github 2024-05-20 10:20:53 -07:00
instantiations Eliminated TConfig. 2024-10-17 05:04:22 -07:00
activations.h Infra improvements (2) 2025-01-23 01:55:19 -08:00
c_api.cc Adds: 2025-02-25 01:00:02 -08:00
c_api.h Adds: 2025-02-25 01:00:02 -08:00
common.cc Rename ModelTraining to PromptWrapping which is a more accurate name. 2024-12-13 07:45:59 -08:00
common.h Rename ModelTraining to PromptWrapping which is a more accurate name. 2024-12-13 07:45:59 -08:00
configs.cc Windows build fixes: struct vs class, unused arg/var, avoid VLA, Deleter arg, casts 2025-02-07 07:38:55 -08:00
configs.h Windows build fixes: struct vs class, unused arg/var, avoid VLA, Deleter arg, casts 2025-02-07 07:38:55 -08:00
configs_test.cc Moved the vit config fields to their own config struct 2025-01-15 01:09:49 -08:00
context.cc Adds: 2025-02-25 01:00:02 -08:00
context.h Adds: 2025-02-25 01:00:02 -08:00
gemma-inl.h Implements FusedSoftmaxAndSampleTopK. 2025-02-16 21:30:06 -08:00
gemma.cc Infra improvements (2) 2025-01-23 01:55:19 -08:00
gemma.h With new matmul, much larger batch sizes are advantageous, default to 256. 2025-02-24 10:21:58 -08:00
kv_cache.cc Add KVCache.DeepCopy() . Will be useful for implementing sampling functionality like beam sampling, parallel sampling, CoT Decoding (à la https://arxiv.org/abs/2402.10200) 2025-02-10 04:10:29 -08:00
kv_cache.h Add KVCache.DeepCopy() . Will be useful for implementing sampling functionality like beam sampling, parallel sampling, CoT Decoding (à la https://arxiv.org/abs/2402.10200) 2025-02-10 04:10:29 -08:00
run.cc Matmul rewrite: fp64 sums, hierarchical parallelization, cache-blocking, autotuning 2025-02-20 08:33:46 -08:00
tensor_index.cc Moved the vit config fields to their own config struct 2025-01-15 01:09:49 -08:00
tensor_index.h Added the TensorInfo arg to the compressor so the shape and scale can be output correctly to the file in future. 2024-12-11 01:26:35 -08:00
tensor_index_test.cc Moved the vit config fields to their own config struct 2025-01-15 01:09:49 -08:00
tokenizer.cc Added ability to load/save a complete model file, including tokenizer. 2024-12-19 07:59:41 -08:00
tokenizer.h Adds: 2025-02-25 01:00:02 -08:00
weights.cc Fix the link error when building `compress_weights` with Clang on macOS 2025-02-09 00:13:25 +08:00
weights.h Fix the link error when building `compress_weights` with Clang on macOS 2025-02-09 00:13:25 +08:00