ggml: disable CUDA graphs for unsupported DUP and CONT node types (llama/12891)

Fixes #12798

diff --git a/ggml/src/ggml-cuda/ggml-cuda.cu b/ggml/src/ggml-cuda/ggml-cuda.cu
index fafe9633e202796d08ef988447143af712f6722c..4af1897017567205d842dfa0ffca75d87de78e24 100644 (file)
--- a/ggml/src/ggml-cuda/ggml-cuda.cu
+++ b/ggml/src/ggml-cuda/ggml-cuda.cu
@@ -2488,10 +2488,10 @@ static bool check_node_graph_compatibility_and_refresh_copy_ops(ggml_backend_cud
 #endif
         }
 
-        if (node->op == GGML_OP_MUL_MAT_ID) {
+        if (node->op == GGML_OP_MUL_MAT_ID || node->op == GGML_OP_CONT || node->op == GGML_OP_DUP) {
             use_cuda_graph = false; // This node type is not supported by CUDA graph capture
 #ifndef NDEBUG
-            GGML_LOG_DEBUG("%s: disabling CUDA graphs due to mul_mat_id\n", __func__);
+            GGML_LOG_DEBUG("%s: disabling CUDA graphs due to unsupported node type\n", __func__);
 #endif
         }