[Core][VLM] Stack multimodal tensors to represent multiple images within each prompt (#7902)

This commit is contained in:
Peter Salas
2024-08-28 01:53:56 +00:00
committed by GitHub
parent 9c71c97ae2
commit fab5f53e2d
15 changed files with 214 additions and 60 deletions
+1 -2
View File
@@ -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",