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 16, 18:15 UTC
support tqdm in notebooks (#7510)
fzyzcjy committed
Aug 17, 2024 at 00:17 UTC
ec724a725eeeb6ad3b1d69815c9fb41e7f74997c
1 file changed
+1
-1
vllm/entrypoints/llm.py
+1
-1
@@ -1,7 +1,7 @@
1
from contextlib import contextmanager
2
from typing import ClassVar, List, Optional, Sequence, Union, cast, overload
3
4
-from tqdm import tqdm
4
+from tqdm.auto import tqdm
5
from transformers import PreTrainedTokenizer, PreTrainedTokenizerFast
6
7
from vllm.engine.arg_utils import EngineArgs