[torch.compile] Adding torch compile annotations to some models (#9614)

vllm/model_executor/models/baichuan.py

@@ -26,6 +26,7 @@ from torch import nn
 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.distributed import (get_pp_group, get_tensor_model_parallel_rank,
                               get_tensor_model_parallel_world_size)
@@ -250,6 +251,7 @@ class BaiChuanDecoderLayer(nn.Module):
         return hidden_states, residual
 
 
+@support_torch_compile
 class BaiChuanModel(nn.Module):
 
     def __init__(self,