[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/DeepSeek-V2-Chat-multi-gpu.yaml

@@ -1,19 +1,3 @@
-- match:
-    name: "^model\\.layers\\.(0|[1-9]|[12][0-9])\\."
-  replace:
-    class: "default"
-    kwargs:
-      generate_device: "cuda:0"
-      prefill_device: "cuda:0"
-
-- match:
-    name: "(^model\\.layers\\.([345][0-9])\\.)|(model.norm)|(lm_head)"
-  replace:
-    class: "default"
-    kwargs:
-      generate_device: "cuda:1"
-      prefill_device: "cuda:1"
-
 - match:
     name: "^model.embed_tokens"
   replace:
@@ -123,4 +107,20 @@
     kwargs:
       per_layer_prefill_intput_threshold: 0 # 0 is close layer wise prefill
       transfer_map: 
-        30: "cuda:1"
+        30: "cuda:1"
+
+- match:
+    name: "^model\\.layers\\.(0|[1-9]|[12][0-9])\\."
+  replace:
+    class: "default"
+    kwargs:
+      generate_device: "cuda:0"
+      prefill_device: "cuda:0"
+
+- match:
+    name: "(^model\\.layers\\.([345][0-9])\\.)|(model.norm)|(lm_head)"
+  replace:
+    class: "default"
+    kwargs:
+      generate_device: "cuda:1"
+      prefill_device: "cuda:1"