Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

metal : fuse NORM + MUL + ADD, support non-multiples of 4 (#16220)

Browse Source 
* metal : fuse NORM + MUL + ADD

* metal : support norms of non-multiple of 4

* cont : fix comment [no ci]
This commit is contained in:
Georgi Gerganov
2025-09-25 11:30:16 +03:00
committed by GitHub
parent 4ea00794b8
commit dfcd53f7ec
9 changed files with 206 additions and 232 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-metal/ggml-metal-common.cpp
+2
View File
@@ -383,6 +383,7 @@ void ggml_graph_optimize(ggml_cgraph * gf) {
// fuse only ops that start with these operations
// can be expanded when needed
if (node.op() == GGML_OP_ADD ||
node.op() == GGML_OP_NORM ||
node.op() == GGML_OP_RMS_NORM) {
ops[0] = node.op();
@@ -392,6 +393,7 @@ void ggml_graph_optimize(ggml_cgraph * gf) {
// can be expanded when needed
if (gf->nodes[f]->op != GGML_OP_ADD &&
gf->nodes[f]->op != GGML_OP_MUL &&
gf->nodes[f]->op != GGML_OP_NORM &&
gf->nodes[f]->op != GGML_OP_RMS_NORM) {
break;
}