mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2025-01-08 09:41:45 +00:00
2a63caaa69
* ggml: CUDA unary op EXP Signed-off-by: Molly Sophia <mollysophia379@gmail.com> * ggml: rwkv_wkv op CUDA impl Signed-off-by: Molly Sophia <mollysophia379@gmail.com> --------- Signed-off-by: Molly Sophia <mollysophia379@gmail.com>
49 lines
1.7 KiB
Plaintext
49 lines
1.7 KiB
Plaintext
#include "common.cuh"
|
|
|
|
#define CUDA_NEG_BLOCK_SIZE 256
|
|
#define CUDA_STEP_BLOCK_SIZE 256
|
|
#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
|
|
#define CUDA_EXP_BLOCK_SIZE 256
|
|
#define CUDA_HARDSWISH_BLOCK_SIZE 256
|
|
#define CUDA_SQR_BLOCK_SIZE 256
|
|
#define CUDA_SQRT_BLOCK_SIZE 256
|
|
#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);
|
|
|
|
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);
|
|
|
|
void ggml_cuda_op_exp(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);
|
|
|
|
void ggml_cuda_op_sqrt(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|
|
|
|
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);
|