Deploy VLM with AidGen

Introduction

Edge deployment of Vision Language Models (VLMs) refers to the process of compressing, quantizing, and deploying models that originally ran in the cloud onto local devices. This enables offline, low-latency natural language understanding and generation. Based on the AidGen inference engine, this chapter demonstrates the deployment, loading, and conversation workflow of multimodal large models on edge devices.

In this case, the multimodal model inference runs on the device side. C++ code is used to call relevant interfaces to receive user input and return conversation results in real-time.

• Device: IQ8275
• System: Ubuntu 24.04
• Model: Qwen2.5-VL-3B (392x392)

Supported Platforms

Platform	Operation Mode
IQ8275	Ubuntu 24.04

Prerequisites

1. IQ8275 hardware

2. Ubuntu 24.04 system

System Dependency Configuration

Configure the AidLux Package Source

# Download the correct public key
sudo wget -O- https://archive.aidlux.com/ubuntu24/public.key | gpg --dearmor | sudo tee /etc/apt/trusted.gpg.d/private-aidlux.gpg > /dev/null

# Edit the source list file
sudo vim /etc/apt/sources.list.d/private-aidlux.list

# Add the repository provided by AidLux to the source file
deb [arch=arm64 signed-by=/etc/apt/trusted.gpg.d/private-aidlux.gpg] https://archive.aidlux.com/ubuntu24 noble main

# Update the package cache
sudo apt update

After the update is complete, you can use the following command to retrieve the official AidLux SDK dependencies:

sudo apt list | grep aid | grep unknown

# Install software
# Must be installed first (not included with the system)
sudo apt install python3 python3-pip libopencv-dev python3-opencv net-tools
# Must be installed before aidlite
sudo apt install aidlux-aistack-base aidrtcm

# Install aidlite and dependencies
sudo apt install aid-lms aidlms-sdk aidlite-sdk cmake
sudo apt-get install libfmt-dev nlohmann-json3-dev
sudo apt install aidlite-*

# DSP support
sudo apt-get install qcom-fastrpc1
sudo apt-get install qcom-fastrpc-dev

# Install aidgen-sdk
sudo apt install aidgen-qnn240-sdk

# Install mms service
sudo apt install aid-mms

# GPU support
sudo apt-add-repository -s ppa:ubuntu-qcom-iot/qcom-ppa
sudo apt install qcom-adreno-cl1
sudo ln -s /usr/lib/aarch64-linux-gnu/libOpenCL.so.1 /usr/lib/aarch64-linux-gnu/libOpenCL.so

After installation, check that the aidlite and aidgen directories have been added under /usr/local/share:

Device Authorization

Obtain the Device Serial Number

cat  /sys/devices/soc0/serial_number

Obtain the License File

Provide the serial number to APLUX technical staff to generate a device-specific License file, then place it in the /etc/opt/aidlux/license/AidLuxLics directory.

Activate the License

sudo /opt/aidlux/cpf/aid-lms/manager.sh restart

Case Deployment

Step 1: Copy the AidGen SDK Code Example

# Copy the test code
cd /home/ubuntu
cp -r /usr/local/share/aidgen/examples/cpp/aidmlm ./

Step 2: Obtain the Model

Since Qwen2.5-VL-3B (392x392) is currently in the Model Farm Preview section, you need to use the mms command to obtain it.

Using mms requires a Model Farm account login. Please visit Model Farm Account Registration

# Login
mms login

# Search for the model
mms list Qwen2.5-VL-3B

# Download the model
mms get -m Qwen2.5-VL-3B-Instruct_392x392_ -p w4a16 -c qcs8550 -b qnn2.36 -d /home/ubuntu/aidmlm/qwen2.5-vl-3b-392

cd /home/ubuntu/aidmlm/qwen2.5-vl-3b-392
unzip qnn236_qcs8550_cl2048
mv qnn236_qcs8550_cl2048/* /home/ubuntu/aidmlm/

Step 3: Create Configuration File

cd /home/ubuntu/aidmlm
vim config3b_392.json

Create the following json configuration file:

{
    "vision_model_path":"veg.serialized.bin.aidem",
    "pos_embed_cos_path":"position_ids_cos.raw",
    "pos_embed_sin_path":"position_ids_sin.raw",
    "vocab_embed_path":"embedding_weights_151936x2048.raw",
    "window_attention_mask_path":"window_attention_mask.raw",
    "full_attention_mask_path":"full_attention_mask.raw",
    "llm_path_list":[
        "qwen2p5-vl-3b-qnn231-qcs8550-cl2048_1_of_6.serialized.bin.aidem",
        "qwen2p5-vl-3b-qnn231-qcs8550-cl2048_2_of_6.serialized.bin.aidem",
        "qwen2p5-vl-3b-qnn231-qcs8550-cl2048_3_of_6.serialized.bin.aidem",
        "qwen2p5-vl-3b-qnn231-qcs8550-cl2048_4_of_6.serialized.bin.aidem",
        "qwen2p5-vl-3b-qnn231-qcs8550-cl2048_5_of_6.serialized.bin.aidem",
        "qwen2p5-vl-3b-qnn231-qcs8550-cl2048_6_of_6.serialized.bin.aidem"
    ]
}

The file layout is as follows:

/home/ubuntu/aidmlm
├── CMakeLists.txt
├── test_qwen25vl_abort.cpp
├── test_qwen25vl.cpp
├── demo.jpg
├── embedding_weights_151936x2048.raw
├── full_attention_mask.raw
├── position_ids_cos.raw
├── position_ids_sin.raw
├── qwen2p5-vl-3b-qnn231-qcs8550-cl2048_1_of_6.serialized.bin.aidem
├── qwen2p5-vl-3b-qnn231-qcs8550-cl2048_2_of_6.serialized.bin.aidem
├── qwen2p5-vl-3b-qnn231-qcs8550-cl2048_3_of_6.serialized.bin.aidem
├── qwen2p5-vl-3b-qnn231-qcs8550-cl2048_4_of_6.serialized.bin.aidem
├── qwen2p5-vl-3b-qnn231-qcs8550-cl2048_5_of_6.serialized.bin.aidem
├── qwen2p5-vl-3b-qnn231-qcs8550-cl2048_6_of_6.serialized.bin.aidem
├── veg.serialized.bin.aidem
├── window_attention_mask.raw

Step 4: Build and Run

sudo apt update
sudo apt-get install libfmt-dev nlohmann-json3-dev

mkdir build && cd build
cmake .. && make

mv test_qwen25vl /home/ubuntu/aidmlm/

# After successful build, run
cd /home/ubuntu/aidmlm/
./test_qwen25vl "qwen25vl3b392" "config3b_392.json" "demo.jpg" "Please describe the scene in the image"

The test_qwen25vl.cpp test code defines model_type for different model types as the first argument of the executable. The following model types are currently supported:

Model	Type
Qwen2.5-VL-3B (392X392)	qwen25vl3b392
Qwen2.5-VL-3B (672X672)	qwen25vl3b672
Qwen2.5-VL-7B (392X392)	qwen25vl7b392
Qwen2.5-VL-7B (672X672)	qwen25vl7b672

💡Note

Different downloaded models require the corresponding model_type. For example, if you download the Qwen2.5-VL-7B (672X672) model via aidllm pull api aplux/Qwen2.5-VL-7B-672x672-8550, you should use model_type = "qwen25vl7b672".

• Example output: