CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-04 09:32:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

metal : adjust support conditions for norm operators (#11671)

Browse Source 
cont #11659

ggml-ci
This commit is contained in:
Georgi Gerganov
2025-02-05 10:57:42 +02:00
committed by GitHub
parent fa62da9b2d
commit d774ab3acc
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
ggml/src/ggml-metal/ggml-metal.m
View File

@@ -1204,13 +1204,13 @@ static bool ggml_metal_supports_op(const struct ggml_backend_metal_device_contex
case GGML_OP_SUM_ROWS:
case GGML_OP_SOFT_MAX:
case GGML_OP_GROUP_NORM:
return has_simdgroup_reduction;
return has_simdgroup_reduction && ggml_is_contiguous(op->src[0]);
case GGML_OP_RMS_NORM:
return has_simdgroup_reduction && (op->ne[0] % 4 == 0 && ggml_is_contiguous_1(op->src[0]));
case GGML_OP_ARGMAX:
return true;
case GGML_OP_NORM:
return has_simdgroup_reduction && ggml_is_contiguous(op->src[0]);
return has_simdgroup_reduction && (op->ne[0] % 4 == 0 && ggml_is_contiguous_1(op->src[0]));
case GGML_OP_ROPE:
{
const int mode = ((const int32_t *) op->op_params)[2];