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

[Misc] Move some multimodal utils to modality-specific modules (#11494)

Browse Source 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung
2024-12-26 12:23:20 +08:00
committed by GitHub
parent 6ad909fdda
commit 51a624bf02
13 changed files with 84 additions and 77 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tests/models/encoder_decoder/vision_language/test_mllama.py
View File

@@ -6,7 +6,7 @@ from transformers import (AutoConfig, AutoModelForVision2Seq, AutoTokenizer,
from vllm.attention.selector import (_Backend, _cached_get_attn_backend,
global_force_attn_backend_context_manager)
from vllm.multimodal.utils import rescale_image_size
from vllm.multimodal.image import rescale_image_size
from vllm.sequence import SampleLogprobs
from ....conftest import (IMAGE_ASSETS, HfRunner, PromptImageInput, VllmRunner,