mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-11-14 14:59:52 +00:00
28 lines
981 B
Plaintext
28 lines
981 B
Plaintext
|
#include "common.cuh"
|
||
|
|
||
|
#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_HARDSIGMOID_BLOCK_SIZE 256
|
||
|
#define CUDA_HARDSWISH_BLOCK_SIZE 256
|
||
|
#define CUDA_SQR_BLOCK_SIZE 256
|
||
|
|
||
|
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_hardsigmoid(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|
||
|
|
||
|
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);
|