google / gemma.cpp

lightweight, standalone C++ inference engine for Google's Gemma models.
Apache License 2.0
5.9k stars 499 forks source link

Fix RecurrentGemma (refs #166) - one Dot was ignoring scale. #179

Closed copybara-service[bot] closed 4 months ago

copybara-service[bot] commented 4 months ago

Fix RecurrentGemma (refs #166) - one Dot was ignoring scale.

Remove extra Dot() overload MatVecAdd always adds, use MatVecT if conditional. Remove ununsed MatVecAddLoop and MatVecLoop No longer tsan-verify even_odd