多模態輸入¶
本頁介紹如何在 vLLM 中將多模態輸入傳遞給多模態模型。
注意
我們正在積極迭代多模態支援。有關即將進行的更改，請參閱此RFC；如果您有任何反饋或功能請求，請在GitHub上提交一個issue。
離線推理¶
要輸入多模態資料，請遵循vllm.inputs.PromptType中的此模式：
prompt：提示應遵循HuggingFace上文件中定義的格式。multi_modal_data：這是一個字典，遵循vllm.multimodal.inputs.MultiModalDataDict中定義的模式。
影像輸入¶
您可以將單個影像傳遞給多模態字典的'image'欄位，如下例所示
程式碼
from vllm import LLM
llm = LLM(model="llava-hf/llava-1.5-7b-hf")
# Refer to the HuggingFace repo for the correct format to use
prompt = "USER: <image>\nWhat is the content of this image?\nASSISTANT:"
# Load the image using PIL.Image
image = PIL.Image.open(...)
# Single prompt inference
outputs = llm.generate({
"prompt": prompt,
"multi_modal_data": {"image": image},
})
for o in outputs:
generated_text = o.outputs[0].text
print(generated_text)
# Batch inference
image_1 = PIL.Image.open(...)
image_2 = PIL.Image.open(...)
outputs = llm.generate(
[
{
"prompt": "USER: <image>\nWhat is the content of this image?\nASSISTANT:",
"multi_modal_data": {"image": image_1},
},
{
"prompt": "USER: <image>\nWhat's the color of this image?\nASSISTANT:",
"multi_modal_data": {"image": image_2},
}
]
)
for o in outputs:
generated_text = o.outputs[0].text
print(generated_text)
完整示例： examples/offline_inference/vision_language.py
要在同一文字提示中替換多張影像，您可以傳遞一個影像列表
程式碼
from vllm import LLM
llm = LLM(
model="microsoft/Phi-3.5-vision-instruct",
trust_remote_code=True, # Required to load Phi-3.5-vision
max_model_len=4096, # Otherwise, it may not fit in smaller GPUs
limit_mm_per_prompt={"image": 2}, # The maximum number to accept
)
# Refer to the HuggingFace repo for the correct format to use
prompt = "<|user|>\n<|image_1|>\n<|image_2|>\nWhat is the content of each image?<|end|>\n<|assistant|>\n"
# Load the images using PIL.Image
image1 = PIL.Image.open(...)
image2 = PIL.Image.open(...)
outputs = llm.generate({
"prompt": prompt,
"multi_modal_data": {
"image": [image1, image2]
},
})
for o in outputs:
generated_text = o.outputs[0].text
print(generated_text)
完整示例： examples/offline_inference/vision_language_multi_image.py
如果使用LLM.chat方法，您可以直接在訊息內容中以各種格式傳遞影像：影像URL、PIL Image物件或預計算的嵌入
from vllm import LLM
from vllm.assets.image import ImageAsset
llm = LLM(model="llava-hf/llava-1.5-7b-hf")
image_url = "https://picsum.photos/id/32/512/512"
image_pil = ImageAsset('cherry_blossom').pil_image
image_embeds = torch.load(...)
conversation = [
{"role": "system", "content": "You are a helpful assistant"},
{"role": "user", "content": "Hello"},
{"role": "assistant", "content": "Hello! How can I assist you today?"},
{
"role": "user",
"content": [{
"type": "image_url",
"image_url": {
"url": image_url
}
},{
"type": "image_pil",
"image_pil": image_pil
}, {
"type": "image_embeds",
"image_embeds": image_embeds
}, {
"type": "text",
"text": "What's in these images?"
}],
},
]
# Perform inference and log output.
outputs = llm.chat(conversation)
for o in outputs:
generated_text = o.outputs[0].text
print(generated_text)
多影像輸入可以擴充套件用於影片字幕。我們以支援影片的Qwen2-VL為例進行展示
程式碼
from vllm import LLM
# Specify the maximum number of frames per video to be 4. This can be changed.
llm = LLM("Qwen/Qwen2-VL-2B-Instruct", limit_mm_per_prompt={"image": 4})
# Create the request payload.
video_frames = ... # load your video making sure it only has the number of frames specified earlier.
message = {
"role": "user",
"content": [
{"type": "text", "text": "Describe this set of frames. Consider the frames to be a part of the same video."},
],
}
for i in range(len(video_frames)):
base64_image = encode_image(video_frames[i]) # base64 encoding.
new_image = {"type": "image_url", "image_url": {"url": f"data:image/jpeg;base64,{base64_image}"}}
message["content"].append(new_image)
# Perform inference and log output.
outputs = llm.chat([message])
for o in outputs:
generated_text = o.outputs[0].text
print(generated_text)
影片輸入¶
您可以直接將NumPy陣列列表傳遞給多模態字典的'video'欄位，而不是使用多影像輸入。
除了NumPy陣列，您還可以傳遞'torch.Tensor'例項，如使用Qwen2.5-VL的此示例所示
程式碼
from transformers import AutoProcessor
from vllm import LLM, SamplingParams
from qwen_vl_utils import process_vision_info
model_path = "Qwen/Qwen2.5-VL-3B-Instruct/"
video_path = "https://content.pexels.com/videos/free-videos.mp4"
llm = LLM(
model=model_path,
gpu_memory_utilization=0.8,
enforce_eager=True,
limit_mm_per_prompt={"video": 1},
)
sampling_params = SamplingParams(
max_tokens=1024,
)
video_messages = [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": [
{"type": "text", "text": "describe this video."},
{
"type": "video",
"video": video_path,
"total_pixels": 20480 * 28 * 28,
"min_pixels": 16 * 28 * 28
}
]
},
]
messages = video_messages
processor = AutoProcessor.from_pretrained(model_path)
prompt = processor.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True,
)
image_inputs, video_inputs = process_vision_info(messages)
mm_data = {}
if video_inputs is not None:
mm_data["video"] = video_inputs
llm_inputs = {
"prompt": prompt,
"multi_modal_data": mm_data,
}
outputs = llm.generate([llm_inputs], sampling_params=sampling_params)
for o in outputs:
generated_text = o.outputs[0].text
print(generated_text)
注意
'process_vision_info' 僅適用於Qwen2.5-VL及類似模型。
完整示例： examples/offline_inference/vision_language.py
音訊輸入¶
您可以將元組(array, sampling_rate)傳遞給多模態字典的'audio'欄位。
完整示例： examples/offline_inference/audio_language.py
嵌入輸入¶
要將屬於特定資料型別（即影像、影片或音訊）的預計算嵌入直接輸入到語言模型，請將形狀為(num_items, feature_size, hidden_size of LM)的張量傳遞給多模態字典的相應欄位。
程式碼
from vllm import LLM
# Inference with image embeddings as input
llm = LLM(model="llava-hf/llava-1.5-7b-hf")
# Refer to the HuggingFace repo for the correct format to use
prompt = "USER: <image>\nWhat is the content of this image?\nASSISTANT:"
# Embeddings for single image
# torch.Tensor of shape (1, image_feature_size, hidden_size of LM)
image_embeds = torch.load(...)
outputs = llm.generate({
"prompt": prompt,
"multi_modal_data": {"image": image_embeds},
})
for o in outputs:
generated_text = o.outputs[0].text
print(generated_text)
對於Qwen2-VL和MiniCPM-V，我們接受與嵌入並行的附加引數
程式碼
# Construct the prompt based on your model
prompt = ...
# Embeddings for multiple images
# torch.Tensor of shape (num_images, image_feature_size, hidden_size of LM)
image_embeds = torch.load(...)
# Qwen2-VL
llm = LLM("Qwen/Qwen2-VL-2B-Instruct", limit_mm_per_prompt={"image": 4})
mm_data = {
"image": {
"image_embeds": image_embeds,
# image_grid_thw is needed to calculate positional encoding.
"image_grid_thw": torch.load(...), # torch.Tensor of shape (1, 3),
}
}
# MiniCPM-V
llm = LLM("openbmb/MiniCPM-V-2_6", trust_remote_code=True, limit_mm_per_prompt={"image": 4})
mm_data = {
"image": {
"image_embeds": image_embeds,
# image_sizes is needed to calculate details of the sliced image.
"image_sizes": [image.size for image in images], # list of image sizes
}
}
outputs = llm.generate({
"prompt": prompt,
"multi_modal_data": mm_data,
})
for o in outputs:
generated_text = o.outputs[0].text
print(generated_text)
線上服務¶
我們的OpenAI相容伺服器透過Chat Completions API接受多模態資料。
重要
使用Chat Completions API需要聊天模板。對於HF格式模型，預設聊天模板在chat_template.json或tokenizer_config.json中定義。
如果沒有可用的預設聊天模板，我們將首先在 vllm/transformers_utils/chat_templates/registry.py中查詢內建的回退模板。如果沒有回退模板可用，將引發錯誤，您必須透過--chat-template引數手動提供聊天模板。
對於某些模型，我們在 examples中提供了替代的聊天模板。例如，VLM2Vec 使用 examples/template_vlm2vec.jinja，這與Phi-3-Vision的預設模板不同。
影像輸入¶
影像輸入根據OpenAI Vision API提供支援。以下是使用Phi-3.5-Vision的簡單示例。
首先，啟動OpenAI相容伺服器
vllm serve microsoft/Phi-3.5-vision-instruct --task generate \
--trust-remote-code --max-model-len 4096 --limit-mm-per-prompt '{"image":2}'
然後，您可以按如下方式使用OpenAI客戶端
程式碼
from openai import OpenAI
openai_api_key = "EMPTY"
openai_api_base = "https://:8000/v1"
client = OpenAI(
api_key=openai_api_key,
base_url=openai_api_base,
)
# Single-image input inference
image_url = "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg"
chat_response = client.chat.completions.create(
model="microsoft/Phi-3.5-vision-instruct",
messages=[{
"role": "user",
"content": [
# NOTE: The prompt formatting with the image token `<image>` is not needed
# since the prompt will be processed automatically by the API server.
{"type": "text", "text": "What’s in this image?"},
{"type": "image_url", "image_url": {"url": image_url}},
],
}],
)
print("Chat completion output:", chat_response.choices[0].message.content)
# Multi-image input inference
image_url_duck = "https://upload.wikimedia.org/wikipedia/commons/d/da/2015_Kaczka_krzy%C5%BCowka_w_wodzie_%28samiec%29.jpg"
image_url_lion = "https://upload.wikimedia.org/wikipedia/commons/7/77/002_The_lion_king_Snyggve_in_the_Serengeti_National_Park_Photo_by_Giles_Laurent.jpg"
chat_response = client.chat.completions.create(
model="microsoft/Phi-3.5-vision-instruct",
messages=[{
"role": "user",
"content": [
{"type": "text", "text": "What are the animals in these images?"},
{"type": "image_url", "image_url": {"url": image_url_duck}},
{"type": "image_url", "image_url": {"url": image_url_lion}},
],
}],
)
print("Chat completion output:", chat_response.choices[0].message.content)
完整示例： examples/online_serving/openai_chat_completion_client_for_multimodal.py
提示
vLLM 也支援從本地檔案路徑載入：您可以在啟動API伺服器/引擎時透過--allowed-local-media-path指定允許的本地媒體路徑，並在API請求中將檔案路徑作為url傳遞。
提示
無需在API請求的文字內容中放置影像佔位符——它們已經由影像內容表示。實際上，您可以透過交錯文字和影像內容的方式，將影像佔位符放置在文字中間。
影片輸入¶
除了image_url，您還可以透過video_url傳遞影片檔案。以下是使用LLaVA-OneVision的簡單示例。
首先，啟動OpenAI相容伺服器
然後，您可以按如下方式使用OpenAI客戶端
程式碼
from openai import OpenAI
openai_api_key = "EMPTY"
openai_api_base = "https://:8000/v1"
client = OpenAI(
api_key=openai_api_key,
base_url=openai_api_base,
)
video_url = "http://commondatastorage.googleapis.com/gtv-videos-bucket/sample/ForBiggerFun.mp4"
## Use video url in the payload
chat_completion_from_url = client.chat.completions.create(
messages=[{
"role":
"user",
"content": [
{
"type": "text",
"text": "What's in this video?"
},
{
"type": "video_url",
"video_url": {
"url": video_url
},
},
],
}],
model=model,
max_completion_tokens=64,
)
result = chat_completion_from_url.choices[0].message.content
print("Chat completion output from image url:", result)
完整示例： examples/online_serving/openai_chat_completion_client_for_multimodal.py
音訊輸入¶
音訊輸入根據OpenAI Audio API提供支援。以下是使用Ultravox-v0.5-1B的簡單示例。
首先，啟動OpenAI相容伺服器
然後，您可以按如下方式使用OpenAI客戶端
程式碼
import base64
import requests
from openai import OpenAI
from vllm.assets.audio import AudioAsset
def encode_base64_content_from_url(content_url: str) -> str:
"""Encode a content retrieved from a remote url to base64 format."""
with requests.get(content_url) as response:
response.raise_for_status()
result = base64.b64encode(response.content).decode('utf-8')
return result
openai_api_key = "EMPTY"
openai_api_base = "https://:8000/v1"
client = OpenAI(
api_key=openai_api_key,
base_url=openai_api_base,
)
# Any format supported by librosa is supported
audio_url = AudioAsset("winning_call").url
audio_base64 = encode_base64_content_from_url(audio_url)
chat_completion_from_base64 = client.chat.completions.create(
messages=[{
"role": "user",
"content": [
{
"type": "text",
"text": "What's in this audio?"
},
{
"type": "input_audio",
"input_audio": {
"data": audio_base64,
"format": "wav"
},
},
],
}],
model=model,
max_completion_tokens=64,
)
result = chat_completion_from_base64.choices[0].message.content
print("Chat completion output from input audio:", result)
或者，您可以傳遞audio_url，它是影像輸入中image_url的音訊對應項
程式碼
chat_completion_from_url = client.chat.completions.create(
messages=[{
"role": "user",
"content": [
{
"type": "text",
"text": "What's in this audio?"
},
{
"type": "audio_url",
"audio_url": {
"url": audio_url
},
},
],
}],
model=model,
max_completion_tokens=64,
)
result = chat_completion_from_url.choices[0].message.content
print("Chat completion output from audio url:", result)
完整示例： examples/online_serving/openai_chat_completion_client_for_multimodal.py
嵌入輸入¶
要將屬於特定資料型別（即影像、影片或音訊）的預計算嵌入直接輸入到語言模型，請將張量傳遞給多模態字典的相應欄位。
影像嵌入輸入¶
對於影像嵌入，您可以將base64編碼的張量傳遞給image_embeds欄位。以下示例演示瞭如何將影像嵌入傳遞給OpenAI伺服器
程式碼
image_embedding = torch.load(...)
grid_thw = torch.load(...) # Required by Qwen/Qwen2-VL-2B-Instruct
buffer = io.BytesIO()
torch.save(image_embedding, buffer)
buffer.seek(0)
binary_data = buffer.read()
base64_image_embedding = base64.b64encode(binary_data).decode('utf-8')
client = OpenAI(
# defaults to os.environ.get("OPENAI_API_KEY")
api_key=openai_api_key,
base_url=openai_api_base,
)
# Basic usage - this is equivalent to the LLaVA example for offline inference
model = "llava-hf/llava-1.5-7b-hf"
embeds = {
"type": "image_embeds",
"image_embeds": f"{base64_image_embedding}"
}
# Pass additional parameters (available to Qwen2-VL and MiniCPM-V)
model = "Qwen/Qwen2-VL-2B-Instruct"
embeds = {
"type": "image_embeds",
"image_embeds": {
"image_embeds": f"{base64_image_embedding}" , # Required
"image_grid_thw": f"{base64_image_grid_thw}" # Required by Qwen/Qwen2-VL-2B-Instruct
},
}
model = "openbmb/MiniCPM-V-2_6"
embeds = {
"type": "image_embeds",
"image_embeds": {
"image_embeds": f"{base64_image_embedding}" , # Required
"image_sizes": f"{base64_image_sizes}" # Required by openbmb/MiniCPM-V-2_6
},
}
chat_completion = client.chat.completions.create(
messages=[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": [
{
"type": "text",
"text": "What's in this image?",
},
embeds,
],
},
],
model=model,
)
注意
僅一個訊息可以包含{"type": "image_embeds"}。如果與需要額外引數的模型一起使用，您還必須為每個引數提供一個張量，例如image_grid_thw、image_sizes等。