CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-21 12:16:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

cuda : add ELU support (#14657)

Browse Source
This commit is contained in:
Yavor Ivanov
2025-07-13 02:33:16 -07:00
committed by GitHub
parent 05fec5bd29
commit e743cddb60
3 changed files with 13 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
ggml/src/ggml-cuda/unary.cu
View File

@@ -83,6 +83,10 @@ static __device__ __forceinline__ float op_log(float x) {
return logf(x);
}
static __device__ __forceinline__ float op_elu(float x) {
return (x > 0.f) ? x : expm1f(x);
}
template <float (*op)(float), typename T>
static __global__ void unary_op_kernel(const T * x, T * dst, const int k) {
const int i = blockDim.x*blockIdx.x + threadIdx.x;
@@ -196,6 +200,9 @@ void ggml_cuda_op_log(ggml_backend_cuda_context & ctx, ggml_tensor * dst) {
ggml_cuda_op_unary<op_log>(ctx, dst);
}
void ggml_cuda_op_elu(ggml_backend_cuda_context & ctx, ggml_tensor * dst) {
ggml_cuda_op_unary<op_elu>(ctx, dst);
}
/* gated ops */
template <float (*op)(float), typename T>