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, 23:15 UTC
[Bugfix] TYPE_CHECKING for MultiModalData (#5444)
Arthur Kim committed
Jun 13, 2024 at 06:08 UTC
5cc50a531f720758025c8493ee85a56272277a54
1 file changed
+1
-1
vllm/inputs.py
+1
-1
@@ -4,7 +4,7 @@ from typing import (TYPE_CHECKING, List, Literal, Optional, Sequence,
4
from typing_extensions import NotRequired
5
6
if TYPE_CHECKING:
7
- from vllm.sequence import MultiModalData
7
+ from vllm.multimodal import MultiModalData
8
9
10
class ParsedText(TypedDict):