mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-11-14 23:09:53 +00:00
6 lines
142 B
Plaintext
6 lines
142 B
Plaintext
|
#include "common.cuh"
|
||
|
|
|
||
|
|
#define CUDA_SOFT_MAX_BLOCK_SIZE 1024
|
||
|
|
|
||
|
|
void ggml_cuda_op_soft_max(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|