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

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

vllm/model_executor/models/arctic.py

@@ -6,7 +6,7 @@ from torch import nn
 
 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_rank,
                               get_tensor_model_parallel_world_size,
                               tensor_model_parallel_all_reduce)
@@ -415,14 +415,16 @@ class ArcticModel(nn.Module):
 
 class ArcticForCausalLM(nn.Module, SupportsPP):
 
-    def __init__(self,
-                 config: ArcticConfig,
-                 cache_config: Optional[CacheConfig] = None,
-                 quant_config: Optional[QuantizationConfig] = None,
-                 **kwargs) -> 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.model = ArcticModel(config, cache_config, quant_config)
+        self.model = ArcticModel(config,
+                                 cache_config,
+                                 quant_config,
+                                 prefix=prefix)
         self.vocab_size = config.vocab_size
         self.lm_head = ParallelLMHead(
             self.vocab_size,