update chatglm nn layout

vllm/model_executor/models/chatglm.py

@@ -549,6 +549,15 @@ class ChatGLMModel(nn.Module):
         self.make_empty_intermediate_tensors = (
             self.encoder.make_empty_intermediate_tensors)
         
+        self.quant_method = None
+        if quant_config is not None:
+            self.quant_method=quant_config.get_name()
+            self.quant_config=quant_config
+
+        self.use_llama_nn = os.environ.get('LLAMA_NN') == '1'
+        self.use_gemm_pad = os.environ.get('GEMM_PAD') == '1'
+        self.use_fa_pad = os.environ.get('FA_PAD') == '1'
+
     def _parse_and_validate_image_input(
             self, **kwargs: object) -> GLMImagePixelInputs:
 
@@ -732,14 +741,6 @@ class ChatGLMBaseModel(nn.Module, SupportsLoRA, SupportsPP):
         self.logits_processor = LogitsProcessor(config.padded_vocab_size)
 
         self.sampler = get_sampler()
-        self.quant_method = None
-        if quant_config is not None:
-            self.quant_method=quant_config.get_name()
-            self.quant_config=quant_config
-
-        self.use_llama_nn = os.environ.get('LLAMA_NN') == '1'
-        self.use_gemm_pad = os.environ.get('GEMM_PAD') == '1'
-        self.use_fa_pad = os.environ.get('FA_PAD') == '1'
 
     def forward(self,
                 input_ids: torch.Tensor,