1
0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2025-01-24 18:39:19 +01:00
llama.cpp/ggml-cuda/rope.cuh

6 lines
133 B
Plaintext
Raw Normal View History

#include "common.cuh"
#define CUDA_ROPE_BLOCK_SIZE 256
void ggml_cuda_op_rope(ggml_backend_cuda_context & ctx, ggml_tensor * dst);