[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:
co-authored by
Xiaowei Jiang
ywang96
xwjiang2010
Roger Wang
parent
482045ee77
commit
9831aec49f
@@ -92,10 +92,9 @@ class EmbeddingModelRunner(
|
||||
"positions": model_input.input_positions,
|
||||
"kv_caches": kv_caches,
|
||||
"attn_metadata": model_input.attn_metadata,
|
||||
**(model_input.multi_modal_kwargs or {}),
|
||||
}
|
||||
if self.vision_language_config:
|
||||
multi_modal_kwargs = model_input.multi_modal_kwargs or {}
|
||||
execute_model_kwargs.update({"image_input": multi_modal_kwargs})
|
||||
|
||||
hidden_states = model_executable(**execute_model_kwargs)
|
||||
|
||||
# Only perform pooling in the driver worker.
|
||||
|
||||
Reference in New Issue
Block a user