[Core][VLM] Stack multimodal tensors to represent multiple images within each prompt (#7902)
This commit is contained in:
@@ -1,4 +1,4 @@
|
||||
from .base import (BatchedTensorInputs, BatchedTensors, MultiModalDataBuiltins,
|
||||
from .base import (BatchedTensorInputs, MultiModalDataBuiltins,
|
||||
MultiModalDataDict, MultiModalInputs, MultiModalPlugin,
|
||||
NestedTensors)
|
||||
from .registry import MultiModalRegistry
|
||||
@@ -14,7 +14,6 @@ See also:
|
||||
|
||||
__all__ = [
|
||||
"BatchedTensorInputs",
|
||||
"BatchedTensors",
|
||||
"MultiModalDataBuiltins",
|
||||
"MultiModalDataDict",
|
||||
"MultiModalInputs",
|
||||
|
||||
Reference in New Issue
Block a user