@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / a061fe601e
Fork 0

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, 05:45 UTC

[Build][Bugfix] Using the correct type hint (#10866)

Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>

Gregory Shtrasberg committed Dec 3, 2024 at 15:47 UTC a061fe601eb165f11a4808b3ab1ac57d99e0d84e
1 file changed +2 -2
vllm/utils.py
+2 -2
@@ -1540,9 +1540,9 @@ class LazyDict(Mapping[str, T], Generic[T]):
1540 return len(self._factory)
1541
1542
1543 -class ClassRegistry(UserDict[type[T], _V]):
1543 +class ClassRegistry(UserDict[Type[T], _V]):
1544
1545 - def __getitem__(self, key: type[T]) -> _V:
1545 + def __getitem__(self, key: Type[T]) -> _V:
1546 for cls in key.mro():
1547 if cls in self.data:
1548 return self.data[cls]