Allow specifying dtype in langchain.llms.VLLM (#9635)

- Description: add `dtype` argument for VLLM 
  - Issue: #9593 
  - Dependencies: none
  - Tag maintainer: @hwchase17, @baskaryan

libs/langchain/langchain/llms/vllm.py

@@ -59,6 +59,9 @@ class VLLM(BaseLLM):
     logprobs: Optional[int] = None
     """Number of log probabilities to return per output token."""
 
+    dtype: str = "auto"
+    """The data type for the model weights and activations."""
+
     client: Any  #: :meta private:
 
     @root_validator()
@@ -77,6 +80,7 @@ class VLLM(BaseLLM):
             model=values["model"],
             tensor_parallel_size=values["tensor_parallel_size"],
             trust_remote_code=values["trust_remote_code"],
+            dtype=values["dtype"],
         )
 
         return values