Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Bugfix] Fix qwen2.5-vl image processor #13286

Merged
merged 3 commits into from
Feb 15, 2025
+17 −6
Merged

[Bugfix] Fix qwen2.5-vl image processor #13286

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
05183dd
fix qwen2.5-vl image processor
Isotr0py Feb 14, 2025
8319423
check fast version
Isotr0py Feb 14, 2025
43c24d8
handle slow and fast processor for qwen2vl
Isotr0py Feb 14, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 8 additions & 5 deletions vllm/model_executor/models/qwen2_5_vl.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,10 +33,11 @@
import torch.nn.functional as F
from einops import rearrange
from transformers import BatchFeature
from transformers.models.qwen2_5_vl import (Qwen2_5_VLImageProcessor,
Qwen2_5_VLProcessor)
from transformers.models.qwen2_5_vl import Qwen2_5_VLProcessor
from transformers.models.qwen2_5_vl.configuration_qwen2_5_vl import (
Qwen2_5_VLConfig, Qwen2_5_VLVisionConfig)
from transformers.models.qwen2_vl import (Qwen2VLImageProcessor,
Qwen2VLImageProcessorFast)

from vllm.attention import AttentionMetadata
from vllm.config import VllmConfig
Expand Down Expand Up @@ -693,7 +694,8 @@ def get_hf_processor(
) -> Qwen2_5_VLProcessor:
hf_processor = self.ctx.get_hf_processor(Qwen2_5_VLProcessor)
image_processor = hf_processor.image_processor # type: ignore
assert isinstance(image_processor, Qwen2_5_VLImageProcessor)
assert isinstance(image_processor,
(Qwen2VLImageProcessor, Qwen2VLImageProcessorFast))

if min_pixels:
image_processor.min_pixels = min_pixels
Expand All @@ -713,14 +715,15 @@ def get_image_processor(
min_pixels: Optional[int] = None,
max_pixels: Optional[int] = None,
fps: Optional[float] = 2.0,
) -> Qwen2_5_VLImageProcessor:
) -> Union[Qwen2VLImageProcessor, Qwen2VLImageProcessorFast]:
hf_processor = self.get_hf_processor(
min_pixels=min_pixels,
max_pixels=max_pixels,
fps=fps,
)
image_processor = hf_processor.image_processor # type: ignore
assert isinstance(image_processor, Qwen2_5_VLImageProcessor)
assert isinstance(image_processor,
(Qwen2VLImageProcessor, Qwen2VLImageProcessorFast))
return image_processor


Expand Down
10 changes: 9 additions & 1 deletion vllm/model_executor/models/qwen2_vl.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,7 +31,9 @@
import torch.nn as nn
import torch.nn.functional as F
from einops import rearrange, repeat
from packaging.version import Version
from transformers import BatchFeature
from transformers import __version__ as TRANSFORMERS_VERSION
from transformers.models.qwen2_vl import (Qwen2VLImageProcessor,
Qwen2VLProcessor)
from transformers.models.qwen2_vl.configuration_qwen2_vl import (
Expand Down Expand Up @@ -759,7 +761,13 @@ def get_image_processor(
hf_processor = self.get_hf_processor(min_pixels=min_pixels,
max_pixels=max_pixels)
image_processor = hf_processor.image_processor # type: ignore
assert isinstance(image_processor, Qwen2VLImageProcessor)
if Version(TRANSFORMERS_VERSION) >= Version("4.49"):
from transformers.models.qwen2_vl import Qwen2VLImageProcessorFast
assert isinstance(
image_processor,
(Qwen2VLImageProcessor, Qwen2VLImageProcessorFast))
else:
assert isinstance(image_processor, Qwen2VLImageProcessor)
return image_processor

def get_supported_mm_limits(self) -> Mapping[str, Optional[int]]:
Expand Down