[Bugfix] add hf_token to EngineArgs (#16093)

Signed-off-by: paolovic <paul-philipp.luley@uzh.ch>
Co-authored-by: paolovic <paul-philipp.luley@uzh.ch>

vllm/entrypoints/llm.py

@@ -117,6 +117,9 @@ class LLM:
         disable_custom_all_reduce: See :class:`~vllm.config.ParallelConfig`
         disable_async_output_proc: Disable async output processing.
             This may result in lower performance.
+        hf_token: The token to use as HTTP bearer authorization for remote files
+            . If `True`, will use the token generated when running 
+            `huggingface-cli login` (stored in `~/.huggingface`).
         hf_overrides: If a dictionary, contains arguments to be forwarded to the
             HuggingFace config. If a callable, it is called to update the
             HuggingFace config.
@@ -177,6 +180,7 @@ class LLM:
         max_seq_len_to_capture: int = 8192,
         disable_custom_all_reduce: bool = False,
         disable_async_output_proc: bool = False,
+        hf_token: Optional[Union[bool, str]] = None,
         hf_overrides: Optional[HfOverrides] = None,
         mm_processor_kwargs: Optional[dict[str, Any]] = None,
         # After positional args are removed, move this right below `model`
@@ -232,6 +236,7 @@ class LLM:
             max_seq_len_to_capture=max_seq_len_to_capture,
             disable_custom_all_reduce=disable_custom_all_reduce,
             disable_async_output_proc=disable_async_output_proc,
+            hf_token=hf_token,
             hf_overrides=hf_overrides,
             mm_processor_kwargs=mm_processor_kwargs,
             override_pooler_config=override_pooler_config,