unary.cuh 1.71 KB
Newer Older
xuxzh1's avatar
init  
xuxzh1 committed
1
2
#include "common.cuh"

xuxzh1's avatar
update  
xuxzh1 committed
3
4
#define CUDA_NEG_BLOCK_SIZE 256
#define CUDA_STEP_BLOCK_SIZE 256
xuxzh1's avatar
init  
xuxzh1 committed
5
6
7
8
9
10
#define CUDA_GELU_BLOCK_SIZE 256
#define CUDA_SILU_BLOCK_SIZE 256
#define CUDA_TANH_BLOCK_SIZE 256
#define CUDA_RELU_BLOCK_SIZE 256
#define CUDA_SIGMOID_BLOCK_SIZE 256
#define CUDA_HARDSIGMOID_BLOCK_SIZE 256
xuxzh1's avatar
update  
xuxzh1 committed
11
#define CUDA_EXP_BLOCK_SIZE 256
xuxzh1's avatar
init  
xuxzh1 committed
12
13
14
#define CUDA_HARDSWISH_BLOCK_SIZE 256
#define CUDA_SQR_BLOCK_SIZE 256
#define CUDA_SQRT_BLOCK_SIZE 256
xuxzh1's avatar
update  
xuxzh1 committed
15
16
17
18
19
20
#define CUDA_SIN_BLOCK_SIZE 256
#define CUDA_COS_BLOCK_SIZE 256

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

void ggml_cuda_op_step(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
xuxzh1's avatar
init  
xuxzh1 committed
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35

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

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

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

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

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

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

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

xuxzh1's avatar
update  
xuxzh1 committed
36
37
void ggml_cuda_op_exp(ggml_backend_cuda_context & ctx, ggml_tensor * dst);

xuxzh1's avatar
init  
xuxzh1 committed
38
39
40
41
42
43
44
void ggml_cuda_op_hardswish(ggml_backend_cuda_context & ctx, ggml_tensor * dst);

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

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

void ggml_cuda_op_sqrt(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
xuxzh1's avatar
update  
xuxzh1 committed
45
46
47
48

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

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