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 FLOOR, CEIL, ROUND, TRUNC unary ops (#16917)

Browse Source
This commit is contained in:
mnehete32
2025-11-02 08:42:57 +05:30
committed by GitHub
parent a864132ba5
commit 7db35a7958
3 changed files with 56 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

32
ggml/src/ggml-cuda/unary.cu
View File

@@ -85,6 +85,22 @@ static __device__ __forceinline__ float op_elu(float x) {
return (x > 0.f) ? x : expm1f(x);
}
static __device__ __forceinline__ float op_floor(float x) {
return floorf(x);
}
static __device__ __forceinline__ float op_ceil(float x) {
return ceilf(x);
}
static __device__ __forceinline__ float op_round(float x) {
return round(x);
}
static __device__ __forceinline__ float op_trunc(float x) {
return trunc(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;
@@ -201,6 +217,22 @@ void ggml_cuda_op_log(ggml_backend_cuda_context & ctx, ggml_tensor * dst) {
void ggml_cuda_op_elu(ggml_backend_cuda_context & ctx, ggml_tensor * dst) {
ggml_cuda_op_unary<op_elu>(ctx, dst);
}
void ggml_cuda_op_floor(ggml_backend_cuda_context & ctx, ggml_tensor * dst) {
ggml_cuda_op_unary<op_floor>(ctx, dst);
}
void ggml_cuda_op_ceil(ggml_backend_cuda_context & ctx, ggml_tensor * dst) {
ggml_cuda_op_unary<op_ceil>(ctx, dst);
}
void ggml_cuda_op_round(ggml_backend_cuda_context & ctx, ggml_tensor * dst) {
ggml_cuda_op_unary<op_round>(ctx, dst);
}
void ggml_cuda_op_trunc(ggml_backend_cuda_context & ctx, ggml_tensor * dst) {
ggml_cuda_op_unary<op_trunc>(ctx, dst);
}
/* gated ops */
template <float (*op)(float), typename T>