vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

sync : ggml

Browse source
This commit is contained in:
Georgi Gerganov 2024-08-27 22:01:45 +03:00
parent 3246fe84d7
commit 231cff5f6f
21 changed files with 1422 additions and 178 deletions
Download patch file Download diff file Expand all files Collapse all files

6
ggml/src/ggml-cuda/unary.cuh
View file

@ -9,6 +9,8 @@
#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_gelu(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
@ -31,3 +33,7 @@ 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);