Skip to content

ggml-cuda: enable GGML_CUDA_GRAPH_OPT by default on RDNA3.5 #56

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
mgehre-amd merged 1 commit into from
Jul 20, 2026
Merged

ggml-cuda: enable GGML_CUDA_GRAPH_OPT by default on RDNA3.5 #56

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 7 additions & 3 deletions ggml/src/ggml-cuda/ggml-cuda.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4124,9 +4124,13 @@ static void ggml_backend_cuda_graph_optimize(ggml_backend_t backend, ggml_cgraph
GGML_UNUSED(cgraph);
#endif

static bool enable_graph_optimization = [] {
const char * env = getenv("GGML_CUDA_GRAPH_OPT");
return env != nullptr && atoi(env) == 1;
static bool enable_graph_optimization = [cuda_ctx] {
const char * env = getenv("GGML_CUDA_GRAPH_OPT");
if (env != nullptr) {
return atoi(env) == 1;
}
const int cc = ggml_cuda_info().devices[cuda_ctx->device].cc;
return GGML_CUDA_CC_IS_RDNA3_5(cc);
}();

if (!enable_graph_optimization) {
Expand Down
Loading