[5/N] pass the whole config to model (#9983)

Signed-off-by: youkaichao <youkaichao@gmail.com>

vllm/model_executor/models/minicpm.py

@@ -29,7 +29,7 @@ from transformers import PretrainedConfig
 
 from vllm.attention import Attention, AttentionMetadata
 from vllm.compilation.decorators import support_torch_compile
-from vllm.config import CacheConfig, LoRAConfig
+from vllm.config import CacheConfig, LoRAConfig, VllmConfig
 from vllm.distributed import (get_pp_group, get_tensor_model_parallel_rank,
                               get_tensor_model_parallel_world_size,
                               tensor_model_parallel_all_reduce)
@@ -463,12 +463,14 @@ class MiniCPMForCausalLM(nn.Module, SupportsLoRA, SupportsPP):
 
     def __init__(
         self,
-        config: PretrainedConfig,
-        cache_config: Optional[CacheConfig] = None,
-        quant_config: Optional[QuantizationConfig] = None,
-        lora_config: Optional[LoRAConfig] = None,
+        vllm_config: VllmConfig,
+        prefix: str = "",
     ) -> None:
         super().__init__()
+        config = vllm_config.model_config.hf_config
+        cache_config = vllm_config.cache_config
+        quant_config = vllm_config.quant_config
+        lora_config = vllm_config.lora_config
 
         self.config = config
         self.lora_config = lora_config