add ChatGLMForConditionalGeneration

vllm/model_executor/model_loader/utils.py

@@ -23,7 +23,7 @@ def get_model_architecture(
         model_config: ModelConfig) -> Tuple[Type[nn.Module], str]:
     architectures = getattr(model_config.hf_config, "architectures", [])
     visions = getattr(model_config.hf_config, "visual", []) or getattr(model_config.hf_config, "vision_config", [])
-    support_nn_architectures = ['LlamaForCausalLM', 'QWenLMHeadModel', 'Qwen2ForCausalLM', 'Qwen2MoeForCausalLM', 'Qwen2VLForConditionalGeneration', 'ChatGLMModel', 'BaichuanForCausalLM', 'BloomForCausalLM', 'MedusaModel', 'MixtralForCausalLM', 'MLPSpeculatorPreTrainedModel']  
+    support_nn_architectures = ['LlamaForCausalLM', 'QWenLMHeadModel', 'Qwen2ForCausalLM', 'Qwen2MoeForCausalLM', 'Qwen2VLForConditionalGeneration', 'ChatGLMModel', 'ChatGLMForConditionalGeneration', 'BaichuanForCausalLM', 'BloomForCausalLM', 'MedusaModel', 'MixtralForCausalLM', 'MLPSpeculatorPreTrainedModel']  
     if any(arch in architectures for arch in support_nn_architectures): 
         if os.getenv('LLAMA_NN') != '0': 
              if (architectures == ['QWenLMHeadModel'] or architectures == ['ChatGLMModel'] ) and visions != []: