[Core] Dynamic image size support for VLMs (#5276)

Signed-off-by: Xiaowei Jiang <xwjiang2010@gmail.com>
Co-authored-by: Xiaowei Jiang <xwjiang2010@gmail.com>
Co-authored-by: ywang96 <ywang@roblox.com>
Co-authored-by: xwjiang2010 <87673679+xwjiang2010@users.noreply.github.com>
Co-authored-by: Roger Wang <136131678+ywang96@users.noreply.github.com>
This commit is contained in:
Cyrus Leung
2024-07-02 20:34:00 -07:00
committed by GitHub
co-authored by Xiaowei Jiang ywang96 xwjiang2010 Roger Wang
parent 482045ee77
commit 9831aec49f
38 changed files with 1453 additions and 664 deletions
+5 -2
View File
@@ -1,4 +1,5 @@
from .base import MultiModalDataDict, MultiModalPlugin
from .base import (BatchedTensors, MultiModalDataDict, MultiModalInputs,
MultiModalPlugin)
from .registry import MultiModalRegistry
MULTIMODAL_REGISTRY = MultiModalRegistry()
@@ -11,8 +12,10 @@ See also:
"""
__all__ = [
"BatchedTensors",
"MultiModalDataDict",
"MultiModalInputs",
"MultiModalPlugin",
"MULTIMODAL_REGISTRY",
"MultiModalRegistry",
"MultiModalDataDict",
]