EngineX-Ascend/enginex-ascend-910-llama.cpp
10
0
Fork 0
Code Issues Pull Requests Actions 4 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

8
ggml/src/ggml-cuda/unary.cuh
View File

@@ -63,6 +63,14 @@ 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);
void ggml_cuda_op_floor(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
void ggml_cuda_op_ceil(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
void ggml_cuda_op_round(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
void ggml_cuda_op_trunc(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
void ggml_cuda_op_reglu(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
void ggml_cuda_op_geglu(ggml_backend_cuda_context & ctx, ggml_tensor * dst);