Increase performance for Gemma3n models on NVGPUs by enabling CUDA Graph execution (#11525)

* Enable CUDA Graphs for gemma3n.

Similar to
https://github.com/ggml-org/llama.cpp/pull/14741,
though ollama has a slightly different model graph
than llama.cpp which requires different workaround
checks.

* Remove residual check by reshaping differently in gemma3n model

This should make the heuristics more robust

llama/patches/0019-metal-add-mean-kernel-14267.patch

@@ -16,7 +16,7 @@ ggml-ci
  2 files changed, 67 insertions(+), 14 deletions(-)
 
 diff --git a/ggml/src/ggml-metal/ggml-metal.m b/ggml/src/ggml-metal/ggml-metal.m
-index ee4f2dcb..f20f5615 100644
+index a9eeebc6..110c9ece 100644
 --- a/ggml/src/ggml-metal/ggml-metal.m
 +++ b/ggml/src/ggml-metal/ggml-metal.m
 @@ -489,6 +489,7 @@ enum ggml_metal_kernel_type {