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 14, 05:30 UTC
[test utils] correct wrong typing (#26159)
Signed-off-by: Yannick Schnider <yannick.schnider1@ibm.com>
Yannick Schnider committed
Oct 3, 2025 at 11:11 UTC
5446ad1d24ac50d74f6a554651d24b1085fe88a4
1 file changed
+1
-1
tests/conftest.py
+1
-1
@@ -756,7 +756,7 @@ class VllmRunner:
756
757
def get_inputs(
758
self,
759
- prompts: Union[list[str], list[torch.Tensor], list[int]],
759
+ prompts: Union[list[str], list[torch.Tensor], list[list[int]]],
760
images: Optional[PromptImageInput] = None,
761
videos: Optional[PromptVideoInput] = None,
762
audios: Optional[PromptAudioInput] = None,