CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-30 08:42:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

metal : disable support for MUL_MAT F32 x F16

Browse Source
This commit is contained in:
Georgi Gerganov
2024-01-23 15:50:56 +02:00
parent 44879ee885
commit 26d607608d
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
ggml-metal.m
View File

@@ -668,7 +668,8 @@ static bool ggml_metal_supports_op(const struct ggml_metal_context * ctx, const
return true;
case GGML_OP_MUL_MAT:
case GGML_OP_MUL_MAT_ID:
return ctx->support_simdgroup_reduction;
return ctx->support_simdgroup_reduction &&
(op->src[0]->type != GGML_TYPE_F32 || op->src[1]->type == GGML_TYPE_F32);
case GGML_OP_CPY:
case GGML_OP_DUP:
case GGML_OP_CONT: