gemma.cpp/gemma
Zoltan Szabadka f8ccb8e37c Fix kv offset computation for MHA config. 2024-04-30 16:19:14 +00:00
..
benchmark.cc Simplify threading: remove the use of inner_pool. 2024-04-29 16:07:30 +00:00
compress_weights.cc Improve documentation for compress_weights flags 2024-04-29 06:49:50 -07:00
configs.h Support absolute positional embeddings from vanilla transformer 2024-04-25 09:32:14 -07:00
gemma.cc Fix kv offset computation for MHA config. 2024-04-30 16:19:14 +00:00
gemma.h Use more parallelism in the QKV projections in MQA mode. 2024-04-30 13:10:14 +00:00
gemma_test.cc Simplify threading: remove the use of inner_pool. 2024-04-29 16:07:30 +00:00
ops.h Move code to gemma/ so we can remove error-prone copybara: comments. 2024-04-09 04:45:42 -07:00
ops_test.cc Move code to gemma/ so we can remove error-prone copybara: comments. 2024-04-09 04:45:42 -07:00
run.cc Simplify threading: remove the use of inner_pool. 2024-04-29 16:07:30 +00:00