Prep for sharding gemma.cc: split into kv_cache, tokenizer.

google / gemma.cpp

lightweight, standalone C++ inference engine for Google's Gemma models.

Apache License 2.0

5.94k stars 502 forks source link

Closed copybara-service[bot] closed 3 months ago

copybara-service[bot] commented 3 months ago

Prep for sharding gemma.cc: split into kv_cache, tokenizer.

Move activations.h to backprop/ to make space for another activations.h.