biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Bugfix] Loosen type check to avoid errors in V1 (#15021)

Browse Source 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung
2025-03-18 20:54:40 +08:00
committed by GitHub
parent 64fc2193dc
commit ab656f2c2f
9 changed files with 28 additions and 37 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
vllm/model_executor/models/paligemma.py
View File

@@ -23,7 +23,7 @@ from vllm.sequence import IntermediateTensors
from .interfaces import MultiModalEmbeddings, SupportsMultiModal, SupportsPP
from .siglip import SiglipVisionModel
from .utils import (AutoWeightsLoader, init_vllm_registered_model,
from .utils import (AutoWeightsLoader, flatten_bn, init_vllm_registered_model,
maybe_prefix, merge_multimodal_embeddings)
from .vision import get_vision_encoder_info
@@ -270,12 +270,11 @@ class PaliGemmaForConditionalGeneration(nn.Module, SupportsMultiModal,
return None
if pixel_values is not None:
if not isinstance(pixel_values, torch.Tensor):
if not isinstance(pixel_values, (torch.Tensor, list)):
raise ValueError("Incorrect type of pixel values. "
f"Got type: {type(pixel_values)}")
# Remove the N dimension until multiple images are supported.
pixel_values = pixel_values.squeeze(1)
pixel_values = flatten_bn(pixel_values, concat=True)
return PaliGemmaImagePixelInputs(
type="pixel_values",
@@ -287,8 +286,7 @@ class PaliGemmaForConditionalGeneration(nn.Module, SupportsMultiModal,
raise ValueError("Incorrect type of image embeddings. "
f"Got type: {type(image_embeds)}")
# Remove the N dimension until multiple images are supported.
image_embeds = image_embeds.squeeze(1)
image_embeds = flatten_bn(image_embeds, concat=True)
return PaliGemmaImageEmbeddingInputs(
type="image_embeds",