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/compression
History
Jan Wassenberg f6d02b2870 Fix RecurrentGemma (refs #166) - one Dot was ignoring scale. 
Remove extra Dot() overload
MatVecAdd always adds, use MatVecT<kAdd> if conditional.
Remove ununsed MatVecAddLoop and MatVecLoop
No longer tsan-verify even_odd

PiperOrigin-RevId: 631377279
 		2024-05-07 04:40:42 -07:00
..
BUILD Further improve IO, enable multiple backends without -D. 2024-04-19 00:40:29 -07:00
analyze.h Move code to gemma/ so we can remove error-prone copybara: comments. 2024-04-09 04:45:42 -07:00
blob_store.cc Further improve IO, enable multiple backends without -D. 2024-04-19 00:40:29 -07:00
blob_store.h Further improve IO, enable multiple backends without -D. 2024-04-19 00:40:29 -07:00
compress-inl.h Fix RecurrentGemma (refs #166) - one Dot was ignoring scale. 2024-05-07 04:40:42 -07:00
compress.h Further improve IO, enable multiple backends without -D. 2024-04-19 00:40:29 -07:00
distortion.h Update distortion.h to weighted average, add distortion_test. 2024-04-17 01:44:19 -07:00
distortion_test.cc Update distortion.h to weighted average, add distortion_test. 2024-04-17 01:44:19 -07:00
io.cc Further improve IO, enable multiple backends without -D. 2024-04-19 00:40:29 -07:00
io.h Further improve IO, enable multiple backends without -D. 2024-04-19 00:40:29 -07:00
io_win.cc Further improve IO, enable multiple backends without -D. 2024-04-19 00:40:29 -07:00
nuq-inl.h Fix underflow in NUQ ClusterCost() 2024-04-25 11:28:51 -07:00
nuq.h initial commit 2024-02-21 03:31:22 +00:00
nuq_test.cc Update distortion.h to weighted average, add distortion_test. 2024-04-17 01:44:19 -07:00
sfp-inl.h 2x speedup of SFP decode (1.4x overall) on AVX3_DL+. 2024-05-07 01:46:43 -07:00
sfp.h initial commit 2024-02-21 03:31:22 +00:00
sfp_test.cc 2x speedup of SFP decode (1.4x overall) on AVX3_DL+. 2024-05-07 01:46:43 -07:00
stats.cc Move code to gemma/ so we can remove error-prone copybara: comments. 2024-04-09 04:45:42 -07:00
stats.h Further improve IO, enable multiple backends without -D. 2024-04-19 00:40:29 -07:00
test_util.h Update distortion.h to weighted average, add distortion_test. 2024-04-17 01:44:19 -07:00