Skip to content

GitLab

Unverified Commit c36bcfe6 authored by Jiangyun Zhu's avatar Jiangyun Zhu Committed by GitHub
Browse files

[Bugfix] fix dots.ocr pp support (#28705) 


Signed-off-by: default avatarzjy0516 <riverclouds.zhu@qq.com>
parent 529cea34
Hide whitespace changes
Inline Side-by-side
Showing with 4 additions and 0 deletions
vllm/model_executor/models/dots_ocr.py
View file @ c36bcfe6
...@@ -780,6 +780,10 @@ class DotsOCRForCausalLM(nn.Module, SupportsMultiModal, SupportsPP, SupportsLoRA ...@@ -780,6 +780,10 @@ class DotsOCRForCausalLM(nn.Module, SupportsMultiModal, SupportsPP, SupportsLoRA
architectures=["Qwen2ForCausalLM"], architectures=["Qwen2ForCausalLM"],
) )
self.make_empty_intermediate_tensors = (
self.language_model.make_empty_intermediate_tensors
)
def _parse_and_validate_image_input( def _parse_and_validate_image_input(
self, **kwargs: object self, **kwargs: object
) -> DotsOCRImageInputs | None: ) -> DotsOCRImageInputs | None:
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment