CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-20 12:07:33 +00:00
Code Issues Packages Projects Releases Wiki Activity

cuda: fix rope fusion for gemma3 (#17378)

Browse Source
This commit is contained in:
Aman Gupta
2025-11-19 18:25:05 +08:00
committed by GitHub
parent 6fd4f95367
commit fd7353d5eb
1 changed files with 4 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

@@ -3001,6 +3001,10 @@ static void update_cuda_graph_executable(ggml_backend_cuda_context * cuda_ctx) {
static bool ggml_cuda_should_fuse_rope_set_rows(const ggml_tensor * rope,
const ggml_tensor * view,
const ggml_tensor * set_rows) {
if (rope->op != GGML_OP_ROPE || view->op != GGML_OP_VIEW || set_rows->op != GGML_OP_SET_ROWS) {
return false;
}
// ne3 not tested
if (rope->src[0]->ne[3] != 1) {
return false;