CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-14 11:07:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

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);