CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-12 10:47:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

cuda : add Pad Reflect 1D support (#14659)

Browse Source 
* Add Pad Reflect 1D CUDA support

* Update ggml/src/ggml-cuda/pad_reflect_1d.cu

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>

---------

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
This commit is contained in:
Yavor Ivanov
2025-08-22 14:06:29 +03:00
committed by GitHub
parent 9ebebef62f
commit b1ab91821f
3 changed files with 92 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
ggml/src/ggml-cuda/ggml-cuda.cu
View File

@@ -49,6 +49,7 @@
#include "ggml-cuda/wkv.cuh"
#include "ggml-cuda/gla.cuh"
#include "ggml-cuda/set-rows.cuh"
#include "ggml-cuda/pad_reflect_1d.cuh"
#include "ggml.h"
#include <algorithm>
@@ -2352,6 +2353,9 @@ static bool ggml_cuda_compute_forward(ggml_backend_cuda_context & ctx, struct gg
case GGML_OP_PAD:
ggml_cuda_op_pad(ctx, dst);
break;
case GGML_OP_PAD_REFLECT_1D:
ggml_cuda_op_pad_reflect_1d(ctx, dst);
break;
case GGML_OP_ARANGE:
ggml_cuda_op_arange(ctx, dst);
break;
@@ -3490,6 +3494,7 @@ static bool ggml_backend_cuda_device_supports_op(ggml_backend_dev_t dev, const g
return ggml_is_contiguous(op->src[0]);
case GGML_OP_UPSCALE:
case GGML_OP_PAD:
case GGML_OP_PAD_REFLECT_1D:
case GGML_OP_ARANGE:
case GGML_OP_TIMESTEP_EMBEDDING:
case GGML_OP_LEAKY_RELU: