llama.cpp

31953bcf - ggml : add BF16 support to RMS_NORM (CPU, CUDA) (#32135)

ggml : add BF16 support to RMS_NORM (CPU, CUDA) (#32135) * ggml : add BF16 support to RMS_NORM (CPU, CUDA) * cuda : use one helper for the F32/BF16 RMS_NORM launches