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

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

vllm/model_executor/models/persimmon.py

@@ -27,7 +27,7 @@ from transformers import PersimmonConfig
 
 from vllm.attention import Attention, AttentionMetadata
 from vllm.compilation.decorators import support_torch_compile
-from vllm.config import CacheConfig
+from vllm.config import CacheConfig, VllmConfig
 from vllm.distributed import get_pp_group, get_tensor_model_parallel_world_size
 from vllm.model_executor.layers.activation import get_act_fn
 from vllm.model_executor.layers.linear import (ColumnParallelLinear,
@@ -265,11 +265,15 @@ class PersimmonModel(nn.Module):
 
 class PersimmonForCausalLM(nn.Module, SupportsPP):
 
-    def __init__(self,
-                 config: PersimmonConfig,
-                 cache_config: Optional[CacheConfig] = None,
-                 quant_config: Optional[QuantizationConfig] = None):
+    def __init__(
+        self,
+        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
         self.config = config
         self.vocab_size = config.vocab_size
         self.model = PersimmonModel(config,