gemma.cpp/gemma
Charles Chan d67b49d085
Merge 1dfd43a520 into c5c9fc300c
2024-05-08 18:32:35 -06:00
..
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 additional scaling 2024-05-07 08:16:25 -07:00
gemma.cc Support additional scaling 2024-05-07 08:16:25 -07:00
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 Enable even/odd for SFP. Refs #166 2024-05-08 07:09:06 -07:00
ops_test.cc Fix RecurrentGemma (refs #166) - one Dot was ignoring scale. 2024-05-07 04:40:42 -07:00
run-ws.cc run gemma via websocket 2024-04-24 23:29:47 +08:00
run.cc Simplify threading: remove the use of inner_pool. 2024-04-29 16:07:30 +00:00