metal : disable graph concurrency optimization due to bug (#2413)

1 files changed, 4 insertions, 3 deletions

diff --git a/llama.cpp b/llama.cpp
index 024af99..9a8ecdc 100644
--- a/llama.cpp
+++ b/llama.cpp
@@ -1722,9 +1722,10 @@ static bool llama_eval_internal(
 
 #ifdef GGML_USE_METAL
     if (lctx.ctx_metal && N == 1) {
-        if (!ggml_metal_if_optimized(lctx.ctx_metal)) {
-            ggml_metal_graph_find_concurrency(lctx.ctx_metal, gf);
-        }
+        // TODO: disabled until #2413 is resolved
+        //if (!ggml_metal_if_optimized(lctx.ctx_metal)) {
+        //    ggml_metal_graph_find_concurrency(lctx.ctx_metal, gf);
+        //}
         ggml_metal_set_n_cb     (lctx.ctx_metal, n_threads);
         ggml_metal_graph_compute(lctx.ctx_metal, gf);
         ggml_metal_get_tensor   (lctx.ctx_metal, cur);