mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-11-10 10:27:03 +00:00
6 lines
158 B
Plaintext
6 lines
158 B
Plaintext
#include "common.cuh"
|
|
|
|
#define CUDA_SOFTCAP_BLOCK_SIZE 256
|
|
|
|
void ggml_cuda_op_softcap(ggml_backend_cuda_context & ctx, ggml_tensor * dst, ggml_tensor * src);
|