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
Jan Wassenberg 2c28b18eb0 Add NestedPools: one per socket/cluster 
Use in dot_test
app.h: add new flags and rename num_threads to max_threads
matmul: Parallelize MatMulSlow and enable spinning, more large/fewer medium test cases
PiperOrigin-RevId: 683216386
 		2024-10-07 09:40:19 -07:00
..
evals Add MMLU eval to github 2024-05-20 10:20:53 -07:00
instantiations Add support for PaliGemma Vision-LM (224x224) to gemma.cpp 2024-09-23 10:09:38 -07:00
activations.h Add support for PaliGemma Vision-LM (224x224) to gemma.cpp 2024-09-23 10:09:38 -07:00
common.cc Add support for PaliGemma Vision-LM (224x224) to gemma.cpp 2024-09-23 10:09:38 -07:00
common.h Add support for PaliGemma Vision-LM (224x224) to gemma.cpp 2024-09-23 10:09:38 -07:00
configs.h Internal change. 2024-10-02 14:03:34 -07:00
gemma-inl.h Fix MSAN issue for multiturn. Rewind the prior EOS token. 2024-10-07 08:07:54 -07:00
gemma.cc Add support for PaliGemma Vision-LM (224x224) to gemma.cpp 2024-09-23 10:09:38 -07:00
gemma.h 1.09x decode speedup for topk=1/temp0: fuse softmax and sample 2024-09-30 08:37:41 -07:00
kv_cache.cc Major revamp #2 of Prefill: fix token order, parallel for multi-query 2024-07-25 03:28:55 -07:00
kv_cache.h Major revamp #2 of Prefill: fix token order, parallel for multi-query 2024-07-25 03:28:55 -07:00
run.cc Add NestedPools: one per socket/cluster 2024-10-07 09:40:19 -07:00
tokenizer.cc Add support for PaliGemma Vision-LM (224x224) to gemma.cpp 2024-09-23 10:09:38 -07:00
tokenizer.h 7x compile time speedup: shard gemma.cc 2024-07-03 06:35:04 -07:00
weights.cc -467ms startup: parallel Reshape 2024-10-01 04:11:35 -07:00
weights.h Moved Internal code around to simplify 2024-10-03 07:55:21 -07:00