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

[VLM] Remove image_input_type from VLM config (#5852)

Browse Source 
Signed-off-by: Xiaowei Jiang <xwjiang2010@gmail.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: Roger Wang <ywang@roblox.com>
This commit is contained in:
xwjiang2010
2024-07-02 00:57:09 -07:00
committed by GitHub
parent 2c37540aa6
commit 98d6682cd1
35 changed files with 329 additions and 751 deletions
Download Patch File Download Diff File Expand all files Collapse all files

56
examples/llava_example.py
View File

@@ -1,38 +1,32 @@
import argparse
import os
import subprocess
import torch
from PIL import Image
from vllm import LLM
from vllm.multimodal.image import ImageFeatureData, ImagePixelData
# The assets are located at `s3://air-example-data-2/vllm_opensource_llava/`.
# You can use `.buildkite/download-images.sh` to download them
def run_llava_pixel_values(*, disable_image_processor: bool = False):
def run_llava():
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,
disable_image_processor=disable_image_processor,
)
prompt = "<image>" * 576 + (
"\nUSER: What is the content of this image?\nASSISTANT:")
if disable_image_processor:
image = torch.load("images/stop_sign_pixel_values.pt")
else:
image = Image.open("images/stop_sign.jpg")
image = Image.open("images/stop_sign.jpg")
outputs = llm.generate({
"prompt": prompt,
"multi_modal_data": ImagePixelData(image),
"multi_modal_data": {
"image": image
},
})
for o in outputs:
@@ -40,45 +34,11 @@ def run_llava_pixel_values(*, disable_image_processor: bool = False):
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:")
image: torch.Tensor = torch.load("images/stop_sign_image_features.pt")
outputs = llm.generate({
"prompt": prompt,
"multi_modal_data": ImageFeatureData(image),
})
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()
def main():
run_llava()
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"
@@ -95,4 +55,4 @@ if __name__ == "__main__":
local_directory,
"--no-sign-request",
])
main(args)
main()