一、配置环境
# 创建环境
conda create -n demo python=3.10 -y
# 激活环境
conda activate demo
# 安装 torch
conda install pytorch==2.1.2 torchvision==0.16.2 torchaudio==2.1.2 pytorch-cuda=12.1 -c pytorch -c nvidia -y
# 安装其他依赖
pip install transformers==4.38
pip install sentencepiece==0.1.99
pip install einops==0.8.0
pip install protobuf==5.27.2
pip install accelerate==0.33.0
pip install streamlit==1.37.0
创建好的环境如下图所示:
二、InternLM2-Chat-1.8B 模型部署
运行demo:
启动 Streamlit 服务
端口映射:
Web端:
三、LMDeploy 部署 InternLM-XComposer2-VL-1.8B 模型
lmdeploy serve gradio /share/new_models/Shanghai_AI_Laboratory/internlm-xcomposer2-vl-1_8b --cache-max-entry-count 0.1
--cache-max-entry-count:调整GPU中用于KV cache的内存比率
四、LMDeploy 部署 InternVL2-2B 模型
lmdeploy serve gradio /share/new_models/OpenGVLab/InternVL2-2B --cache-max-entry-count 0.1