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

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

vllm/model_executor/models/starcoder2.py

@@ -25,7 +25,7 @@ from transformers import Starcoder2Config
 
 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,
@@ -245,11 +245,15 @@ class Starcoder2Model(nn.Module):
 
 class Starcoder2ForCausalLM(nn.Module, SupportsPP):
 
-    def __init__(self,
-                 config: Starcoder2Config,
-                 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.model = Starcoder2Model(config,
                                      cache_config,