Centralize previous code into GEMMA_DISABLED_TARGETS PiperOrigin-RevId: 772433723
Precompute row pointers. Remove no longer used MHA support; QStride -> qkv_dim. Remove RowPtr from MatMul interface, use only MatPtrT. Require opt-in define for NUQ to speed up builds. Also fix io.cc on Windows. PiperOrigin-RevId: 766228108
Also remove MatPtrT::Packed(); use PackedScale1 instead where const, or Row(0). PiperOrigin-RevId: 764243198
PiperOrigin-RevId: 758199851