tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-17 21:51:27 -04:00
Code Issues Packages Projects Releases Wiki Activity

feat: implemented sigmoid function (ggml/806)

Browse Source 
* added sigmoid function

* implemented metal kernel for sigmoid

* implemented cuda kernel for sigmoid

* added sigmoid unary op and incremented count
This commit is contained in:
Justina Cho
2024-05-01 14:44:26 -07:00
committed by Georgi Gerganov
parent ef0d5e3ec9
commit f5ef34e428
7 changed files with 136 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
ggml-cuda/unary.cuh
View File

@@ -4,6 +4,7 @@
#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_HARDSWISH_BLOCK_SIZE 256
#define CUDA_SQR_BLOCK_SIZE 256
@@ -18,6 +19,8 @@ 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_hardswish(ggml_backend_cuda_context & ctx, ggml_tensor * dst);