A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 14:45 UTC
[misc] use tqdm.auto where appropriate (#16290)
Signed-off-by: Benjamin Kitor <bkitor@gigaio.com>
Benjamin Kitor committed
Apr 9, 2025 at 21:54 UTC
82eb61dd4c4e306bda4f20edab063693396c4e1a
2 files changed
+2
-2
vllm/entrypoints/llm.py
+1
-1
@@ -8,7 +8,7 @@ from typing import Any, Callable, ClassVar, Optional, Union, cast, overload
8
9
import cloudpickle
10
import torch.nn as nn
11
-from tqdm import tqdm
11
+from tqdm.auto import tqdm
12
from typing_extensions import TypeVar, deprecated
13
14
from vllm.beam_search import (BeamSearchInstance, BeamSearchOutput,
vllm/worker/model_runner.py
+1
-1
@@ -15,7 +15,7 @@ import numpy as np
15
import torch
16
import torch.distributed
17
import torch.nn as nn
18
-from tqdm import tqdm
18
+from tqdm.auto import tqdm
19
20
import vllm.envs as envs
21
from vllm.attention import AttentionMetadata, get_attn_backend