char-fork/llama.cpp

git clone https://git.t4t.associates/char-fork/llama.cpp

Johannes Gäßlerggml/examples: add backend support for numerical optimization (ggml/949)424c5d00a2024-09-20

#include "common.cuh"

void ggml_cuda_out_prod(ggml_backend_cuda_context & ctx, ggml_tensor * dst);