Automatically updated from 모델 배포(620:gemma-3-4b-it) by 그룹사용자(groupuser)

config.pbtxt

@@ -1,5 +1,4 @@
-# Triton backend to use.
-name: "gemma-3-4b-it2"
+# Triton Backend for TransformerLLM.
 backend: "python"
 max_batch_size: 0
 
@@ -13,78 +12,6 @@ input [
     dims: [ -1 ]
 
 
-  },
-  {
-    name: "max_length"
-    data_type: TYPE_INT32
-    dims: [ 1 ]
-
-    optional: true
-
-
-  },
-  {
-    name: "max_new_tokens"
-    data_type: TYPE_INT32
-    dims: [ 1 ]
-
-    optional: true
-
-
-  },
-  {
-    name: "do_sample"
-    data_type: TYPE_BOOL
-    dims: [ 1 ]
-
-    optional: true
-
-
-  },
-  {
-    name: "top_k"
-    data_type: TYPE_INT32
-    dims: [ 1 ]
-
-    optional: true
-
-
-  },
-  {
-    name: "top_p"
-    data_type: TYPE_FP32
-    dims: [ 1 ]
-
-    optional: true
-
-
-  },
-  {
-    name: "temperature"
-    data_type: TYPE_FP32
-    dims: [ 1 ]
-
-    optional: true
-
-
-  },
-  {
-    name: "repetition_penalty"
-    data_type: TYPE_FP32
-    dims: [ 1 ]
-
-    optional: true
-
-
-  },
-  {
-    name: "stream"
-    data_type: TYPE_BOOL
-    dims: [ 1 ]
-
-    optional: true
-
-
   }
 
 ]