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

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

vllm/model_executor/models/internlm2_ve.py

@@ -5,7 +5,7 @@ from torch import nn
 from transformers import PretrainedConfig
 
 from vllm.attention import AttentionMetadata
-from vllm.config import CacheConfig
+from vllm.config import CacheConfig, VllmConfig
 from vllm.distributed import get_pp_group
 from vllm.model_executor.layers.layernorm import RMSNorm
 from vllm.model_executor.layers.quantization import QuantizationConfig
@@ -161,11 +161,12 @@ class InternLM2VEForCausalLM(InternLM2ForCausalLM):
 
     def __init__(
         self,
-        config: PretrainedConfig,
-        cache_config: Optional[CacheConfig] = None,
-        quant_config: Optional[QuantizationConfig] = None,
+        vllm_config: VllmConfig,
         prefix: str = "",
     ) -> None:
+        config = vllm_config.model_config.hf_config
+        cache_config = vllm_config.cache_config
+        quant_config = vllm_config.quant_config
         super().__init__(config, cache_config, quant_config)
         self.model = InternLM2VEModel(config,
                                       cache_config,