Skip to content

GitLab

Switch branch/tag
Find file Normal viewHistoryPermalink
llava_example.py 2.58 KB
Newer Older
Rayyyyy's avatar
First add  
Rayyyyy committed
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90 
import argparse
import os
import subprocess

import torch

from vllm import LLM
from vllm.sequence import MultiModalData

# The assets are located at `s3://air-example-data-2/vllm_opensource_llava/`.


def run_llava_pixel_values():
    llm = LLM(
        model="llava-hf/llava-1.5-7b-hf",
        image_input_type="pixel_values",
        image_token_id=32000,
        image_input_shape="1,3,336,336",
        image_feature_size=576,
    )

    prompt = "<image>" * 576 + (
        "\nUSER: What is the content of this image?\nASSISTANT:")

    # This should be provided by another online or offline component.
    images = torch.load("images/stop_sign_pixel_values.pt")

    outputs = llm.generate(prompt,
                           multi_modal_data=MultiModalData(
                               type=MultiModalData.Type.IMAGE, data=images))
    for o in outputs:
        generated_text = o.outputs[0].text
        print(generated_text)


def run_llava_image_features():
    llm = LLM(
        model="llava-hf/llava-1.5-7b-hf",
        image_input_type="image_features",
        image_token_id=32000,
        image_input_shape="1,576,1024",
        image_feature_size=576,
    )

    prompt = "<image>" * 576 + (
        "\nUSER: What is the content of this image?\nASSISTANT:")

    # This should be provided by another online or offline component.
    images = torch.load("images/stop_sign_image_features.pt")

    outputs = llm.generate(prompt,
                           multi_modal_data=MultiModalData(
                               type=MultiModalData.Type.IMAGE, data=images))
    for o in outputs:
        generated_text = o.outputs[0].text
        print(generated_text)


def main(args):
    if args.type == "pixel_values":
        run_llava_pixel_values()
    else:
        run_llava_image_features()


if __name__ == "__main__":
    parser = argparse.ArgumentParser(description="Demo on Llava")
    parser.add_argument("--type",
                        type=str,
                        choices=["pixel_values", "image_features"],
                        default="pixel_values",
                        help="image input type")
    args = parser.parse_args()
    # Download from s3
    s3_bucket_path = "s3://air-example-data-2/vllm_opensource_llava/"
    local_directory = "images"

    # Make sure the local directory exists or create it
    os.makedirs(local_directory, exist_ok=True)

    # Use AWS CLI to sync the directory, assume anonymous access
    subprocess.check_call([
        "aws",
        "s3",
        "sync",
        s3_bucket_path,
        local_directory,
        "--no-sign-request",
    ])
    main(args)