llama.cpp

95a6c595 - ggml: move op parameters from tensors to ggml_tensor::op_params (#2333)

ggml: move op parameters from tensors to ggml_tensor::op_params (#2333) * ggml: move op parameters from tensors to ggml_tensor::op_params * alibi: use memcpy for float params * remove `src[1] = NULL` in ops