L2G3000-LMDeploy 量化部署实践

LMDeploy 量化部署实践闯关任务

环境配置

conda create -n lmdeploy  python=3.10 -y
conda activate lmdeploy
conda install pytorch==2.1.2 torchvision==0.16.2 torchaudio==2.1.2 pytorch-cuda=12.1 -c pytorch -c nvidia -y
pip install timm==1.0.8 openai==1.40.3 lmdeploy[all]==0.5.3

pip install datasets==2.19.2

创建文件夹并设置开发机共享目录的软链接。

mkdir /root/models
ln -s /root/share/new_models/Shanghai_AI_Laboratory/internlm2_5-7b-chat /root/models
ln -s /root/share/new_models/Shanghai_AI_Laboratory/internlm2_5-1_8b-chat /root/models
ln -s /root/share/new_models/OpenGVLab/InternVL2-26B /root/models

启动InternLM2_5-1_8b-chat

lmdeploy chat /root/models/internlm2_5-1_8b-chat

API部署

lmdeploy serve api_server \
    /root/models/internlm2_5-1_8b-chat \
    --model-format hf \
    --quant-policy 0 \
    --server-name 0.0.0.0 \
    --server-port 23333 \
    --tp 1

以命令行形式连接API服务器
关闭http://127.0.0.1:23333网页，但保持终端和本地窗口不动，新建一个终端。

以Gradio网页形式连接API服务器

lmdeploy serve gradio http://localhost:23333 \
    --server-name 0.0.0.0 \
    --server-port 6006

W4A16 量化+ KV cache+KV cache 量化

lmdeploy serve api_server \
    /root/models/internlm2_5-1_8b-chat-w4a16-4bit/ \
    --model-format awq \
    --quant-policy 4 \
    --cache-max-entry-count 0.4\
    --server-name 0.0.0.0 \
    --server-port 23333 \
    --tp 1

原模型

量化后

量化后做kv cache

lmdeploy serve api_server \
    /root/models/internlm2_5-1_8b-chat-w4a16-4bit/ \
    --model-format awq \
    --quant-policy 4 \
    --cache-max-entry-count 0.4\
    --server-name 0.0.0.0 \
    --server-port 23333 \
    --tp 1

Function call

conda activate lmdeploy
lmdeploy serve api_server \
    /root/models/internlm2_5-7b-chat \
    --model-format hf \
    --quant-policy 0 \
    --server-name 0.0.0.0 \
    --server-port 23333 \
    --tp 1

touch /root/internlm2_5_func.py

from openai import OpenAI


def add(a: int, b: int):
    return a + b


def mul(a: int, b: int):
    return a * b


tools = [{
    'type': 'function',
    'function': {
        'name': 'add',
        'description': 'Compute the sum of two numbers',
        'parameters': {
            'type': 'object',
            'properties': {
                'a': {
                    'type': 'int',
                    'description': 'A number',
                },
                'b': {
                    'type': 'int',
                    'description': 'A number',
                },
            },
            'required': ['a', 'b'],
        },
    }
}, {
    'type': 'function',
    'function': {
        'name': 'mul',
        'description': 'Calculate the product of two numbers',
        'parameters': {
            'type': 'object',
            'properties': {
                'a': {
                    'type': 'int',
                    'description': 'A number',
                },
                'b': {
                    'type': 'int',
                    'description': 'A number',
                },
            },
            'required': ['a', 'b'],
        },
    }
}]
messages = [{'role': 'user', 'content': 'Compute (3+5)*2'}]

client = OpenAI(api_key='YOUR_API_KEY', base_url='http://0.0.0.0:23333/v1')
model_name = client.models.list().data[0].id
response = client.chat.completions.create(
    model=model_name,
    messages=messages,
    temperature=0.8,
    top_p=0.8,
    stream=False,
    tools=tools)
print(response)
func1_name = response.choices[0].message.tool_calls[0].function.name
func1_args = response.choices[0].message.tool_calls[0].function.arguments
func1_out = eval(f'{func1_name}(**{func1_args})')
print(func1_out)

messages.append({
    'role': 'assistant',
    'content': response.choices[0].message.content
})
messages.append({
    'role': 'environment',
    'content': f'3+5={func1_out}',
    'name': 'plugin'
})
response = client.chat.completions.create(
    model=model_name,
    messages=messages,
    temperature=0.8,
    top_p=0.8,
    stream=False,
    tools=tools)
print(response)
func2_name = response.choices[0].message.tool_calls[0].function.name
func2_args = response.choices[0].message.tool_calls[0].function.arguments
func2_out = eval(f'{func2_name}(**{func2_args})')
print(func2_out)

python /root/internlm2_5_func.py

遇到如下问题proxys报错问题，把httpx版本改为0.27.0