[misc] use tqdm.auto where appropriate (#16290)

Signed-off-by: Benjamin Kitor <bkitor@gigaio.com>

vllm/entrypoints/llm.py

@@ -8,7 +8,7 @@ from typing import Any, Callable, ClassVar, Optional, Union, cast, overload
 
 import cloudpickle
 import torch.nn as nn
-from tqdm import tqdm
+from tqdm.auto import tqdm
 from typing_extensions import TypeVar, deprecated
 
 from vllm.beam_search import (BeamSearchInstance, BeamSearchOutput,

vllm/worker/model_runner.py

@@ -15,7 +15,7 @@ import numpy as np
 import torch
 import torch.distributed
 import torch.nn as nn
-from tqdm import tqdm
+from tqdm.auto import tqdm
 
 import vllm.envs as envs
 from vllm.attention import AttentionMetadata, get_attn_backend