CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-27 08:21:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

ggml : add ggml_gelu_erf() CUDA kernel (#13719)

Browse Source 
* ggml : add ggml_gelu_erf() CUDA kernel

* missing semicolon
This commit is contained in:
Xuan-Son Nguyen
2025-05-24 13:06:47 +02:00
committed by GitHub
parent c3a2624339
commit 4c32832c59
3 changed files with 16 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
ggml/src/ggml-cuda/ggml-cuda.cu
View File

@@ -2192,6 +2192,9 @@ static bool ggml_cuda_compute_forward(ggml_backend_cuda_context & ctx, struct gg
case GGML_UNARY_OP_SILU:
ggml_cuda_op_silu(ctx, dst);
break;
case GGML_UNARY_OP_GELU_ERF:
ggml_cuda_op_gelu_erf(ctx, dst);
break;
case GGML_UNARY_OP_GELU_QUICK:
ggml_cuda_op_gelu_quick(ctx, dst);
break;
@@ -2977,6 +2980,7 @@ static bool ggml_backend_cuda_device_supports_op(ggml_backend_dev_t dev, const g
case GGML_UNARY_OP_SIGMOID:
case GGML_UNARY_OP_HARDSIGMOID:
case GGML_UNARY_OP_HARDSWISH:
case GGML_UNARY_OP_GELU_ERF:
case GGML_UNARY_OP_GELU_QUICK:
case GGML_UNARY_OP_TANH:
case GGML_UNARY_OP_EXP: