CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-13 10:57:15 +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

16
ggml/src/ggml-cuda/ggml-cuda.cu
View File

@@ -2499,6 +2499,18 @@ static bool ggml_cuda_compute_forward(ggml_backend_cuda_context & ctx, struct gg
case GGML_UNARY_OP_XIELU:
ggml_cuda_op_xielu(ctx, dst);
break;
case GGML_UNARY_OP_FLOOR:
ggml_cuda_op_floor(ctx, dst);
break;
case GGML_UNARY_OP_CEIL:
ggml_cuda_op_ceil(ctx, dst);
break;
case GGML_UNARY_OP_ROUND:
ggml_cuda_op_round(ctx, dst);
break;
case GGML_UNARY_OP_TRUNC:
ggml_cuda_op_trunc(ctx, dst);
break;
default:
return false;
}
@@ -3769,6 +3781,10 @@ static bool ggml_backend_cuda_device_supports_op(ggml_backend_dev_t dev, const g
case GGML_UNARY_OP_TANH:
case GGML_UNARY_OP_EXP:
case GGML_UNARY_OP_ELU:
case GGML_UNARY_OP_FLOOR:
case GGML_UNARY_OP_CEIL:
case GGML_UNARY_OP_ROUND:
case GGML_UNARY_OP_TRUNC:
return ggml_is_contiguous(op->src[0]);
default:
return false;