[feature] experts can be injected using CPUInfer

[fix] fix ktransformers interface when use new CUDAGraphRunner
[fix] fix YAML and optimize logic, the top rule has the highest priority

ktransformers/optimize/optimize_rules/Qwen2-57B-A14B-Instruct-multi-gpu.yaml

@@ -1,10 +1,3 @@
-- match:
-    name: "^model\\.layers\\.([012])\\."
-  replace:
-    class: "default"
-    kwargs:
-      generate_device: "cuda:0"
-      prefill_device: "cuda:0"
 - match:
     name: "^model\\.layers\\.([012])\\."
     class: ktransformers.models.modeling_qwen2_moe.Qwen2MoeRotaryEmbedding
@@ -41,13 +34,6 @@
       out_device: "cuda:0"
   recursive: False # don't recursively inject submodules of this module
 
-- match:
-    name: "^model\\.layers\\.([12][0-9]|[3-9])\\."
-  replace:
-    class: "default"
-    kwargs:
-      generate_device: "cuda:1"
-      prefill_device: "cuda:1"
 - match:
     name: "^model\\.layers\\.([12][0-9]|[3-9])\\."
     class: ktransformers.models.modeling_qwen2_moe.Qwen2MoeRotaryEmbedding
@@ -109,3 +95,18 @@
       transfer_map: 
         3: "cuda:1"
 
+- match:
+    name: "^model\\.layers\\.([012])\\."
+  replace:
+    class: "default"
+    kwargs:
+      generate_device: "cuda:0"
+      prefill_device: "cuda:0"
+
+- match:
+    name: "^model\\.layers\\.([12][0-9]|[3-9])\\."
+  replace:
+    class: "default"
+    kwargs:
+      generate_device: "cuda:1"
+      prefill_device: "cuda:1"