[Core][VLM] Support image embeddings as input (#6613)
This commit is contained in:
@@ -1,6 +1,7 @@
|
||||
from dataclasses import dataclass
|
||||
from typing import Literal
|
||||
|
||||
import torch
|
||||
from PIL import Image
|
||||
|
||||
from vllm.assets.base import get_vllm_public_assets
|
||||
@@ -18,3 +19,12 @@ class ImageAsset:
|
||||
image_path = get_vllm_public_assets(filename=f"{self.name}.jpg",
|
||||
s3_prefix=VLM_IMAGES_DIR)
|
||||
return Image.open(image_path)
|
||||
|
||||
@property
|
||||
def image_embeds(self) -> torch.Tensor:
|
||||
"""
|
||||
Image embeddings, only used for testing purposes with llava 1.5.
|
||||
"""
|
||||
image_path = get_vllm_public_assets(filename=f"{self.name}.pt",
|
||||
s3_prefix=VLM_IMAGES_DIR)
|
||||
return torch.load(image_path)
|
||||
|
||||
Reference in New Issue
Block a user