本文来自社区投稿,作者:Tim 算法工程师
MLC-LLM 是一个呆板学习编译器和高性能大型语言模型部署引擎。该项目的任务是让每个人都能在本身的平台上开辟、优化和部署 AI 模型。InternLM 2.5 是上海人工智能实行室发布的新一代大规模语言模型,相比于之前的版本,InternLM 2.5支持百万长文,推理能力开源领先。本文将带大家手把手使用 MLC-LLM 将 InternLM2.5-1.8B-Chat部署到安卓手机上。
https://github.com/InternLM/InternLM
起首我们来看一下终极的效果~
1. 环境预备
1.1 安装 rust
可参考 https://forge.rust-lang.org/infra/other-installation-methods.html#which
此处使用了国内的镜像,如下列命令,当出现选项时选择 Enter 安装。
- export RUSTUP_DIST_SERVER=https://mirrors.ustc.edu.cn/rust-static
- export RUSTUP_UPDATE_ROOT=https://mirrors.ustc.edu.cn/rust-static/rustup
- curl --proto '=https' --tlsv1.2 -sSf https://mirrors.ustc.edu.cn/misc/rustup-install.sh | sh
复制代码 1.2 安装 Android Studio
可参考 https://developer.android.com/studio
- mkdir -p /root/android && cd /root/android
- wget https://redirector.gvt1.com/edgedl/android/studio/ide-zips/2024.1.1.12/android-studio-2024.1.1.12-linux.tar.gz
- tar -xvzf android-studio-2024.1.1.12-linux.tar.gz
- cd android-studio
- wget https://dl.google.com/android/repository/commandlinetools-linux-11076708_latest.zip?hl=zh-cn
- unzip commandlinetools-linux-11076708_latest.zip\?hl\=zh-cn
- export JAVA_HOME=/root/Downloads/android-studio/jbr
- cmdline-tools/bin/sdkmanager "ndk;27.0.12077973" "cmake;3.22.1" "platforms;android-34" "build-tools;33.0.1" --sdk_root='sdk'
复制代码 1.3 设置环境变量
- . "$HOME/.cargo/env"
- export ANDROID_NDK=/root/android/android-studio/sdk/ndk/27.0.12077973
- export TVM_NDK_CC=$ANDROID_NDK/toolchains/llvm/prebuilt/linux-x86_64/bin/aarch64-linux-android24-clang
- export JAVA_HOME=/root/android//android-studio/jbr
- export ANDROID_HOME=/root/android/android-studio/sdk
- export PATH=/usr/local/cuda-12/bin:$PATH
- export PATH=/root/android/android-studio/sdk/cmake/3.22.1/bin:$PATH
复制代码 2. 转换模型
2.1 安装 mlc-llm
可参考 https://llm.mlc.ai/docs/install/mlc_llm.html (假如下载很慢可以取消重新运行一下,大概本地下载了之后拷已往)
- conda create --name mlc-prebuilt python=3.11
- conda activate mlc-prebuilt
- conda install -c conda-forge git-lfs
- pip install pytorch==2.1.2 torchvision==0.16.2 torchaudio==2.1.2 pytorch-cuda=12.1 transformers sentencepiece protobuf
- wget https://github.com/mlc-ai/package/releases/download/v0.9.dev0/mlc_llm_nightly_cu122-0.1.dev1445-cp311-cp311-manylinux_2_28_x86_64.whl
- wget https://github.com/mlc-ai/package/releases/download/v0.9.dev0/mlc_ai_nightly_cu122-0.15.dev404-cp311-cp311-manylinux_2_28_x86_64.whl
- pip install mlc_ai_nightly_cu122-0.15.dev404-cp311-cp311-manylinux_2_28_x86_64.whl
- pip install mlc_llm_nightly_cu122-0.1.dev1445-cp311-cp311-manylinux_2_28_x86_64.whl
复制代码 测试如下输出说明安装正确
- python -c "import mlc_llm; print(mlc_llm)"
复制代码
克隆项目
- git clone https://github.com/mlc-ai/mlc-llm.git
- cd mlc-llm
- git submodule update --init --recursive
复制代码 2.2 转换参数
使用 mlc_llm 的 convert_weight 对模型参数举行转换和量化,转换后的参数可以跨平台使用
- cd android/MLCChat
- export TVM_SOURCE_DIR=/root/android/mlc-llm/3rdparty/tvm
- export MLC_LLM_SOURCE_DIR=/root/android/mlc-llm
- mlc_llm convert_weight /root/models/internlm2_5-1_8b-chat/ \
- --quantization q4f16_1 \
- -o dist/internlm2_5-1_8b-chat-q4f16_1-MLC
复制代码 2.3 生成设置
使用 mlc_llm 的 gen_config 生成 mlc-chat-config.json 并处置惩罚 tokenizer
出现提示时输入 y
- mlc_llm gen_config /root/models/internlm2_5-1_8b-chat/ \
- --quantization q4f16_1 --conv-template chatml \
- -o dist/internlm2_5-1_8b-chat-q4f16_1-MLC
- Do you wish to run the custom code? [y/N] y
复制代码 2.4 上传到 HuggingF****ace
上传这一步必要能访问 HuggingFace,可能必要部署署理,假如没有署理可以直接在接下来的设置中使用此链接https://huggingface.co/timws/internlm2_5-1_8b-chat-q4f16_1-MLC 中的模型(和文档 https://llm.mlc.ai/docs/deploy/android.html#android-sdk 中的转换方法一样)
2.5 (可选) 测试转换的模型
在打包之前可以测试模型效果,必要编译成二进制文件,已成功在个人电脑上运行测试代码。
- mlc_llm compile ./dist/internlm2_5-1_8b-chat-q4f16_1-MLC/mlc-chat-config.json \
- --device cuda -o dist/libs/internlm2_5-1_8b-chat-q4f16_1-MLC-cuda.so
复制代码 测试编译的模型是否符合预期,手机端运行的效果和测试效果靠近
- from mlc_llm import MLCEngine
- # Create engine
- engine = MLCEngine(model="./dist/internlm2_5-1_8b-chat-q4f16_1-MLC", model_lib="./dist/libs/internlm2_5-1_8b-chat-q4f16_1-MLC-cuda.so")
- # Run chat completion in OpenAI API.
- print(engine)
- for response in engine.chat.completions.create(
- messages=[{"role": "user", "content": "你是谁?"}],
- stream=True
- ):
- for choice in response.choices:
- print(choice.delta.content, end="", flush=True)
- print("\n")
- engine.terminate()
复制代码 3 打包运行
3.1 修改设置文件
修改 mlc-package-config.json,参考如下
- {
- "device": "android",
- "model_list": [
- {
- "model": "HF://timws/internlm2_5-1_8b-chat-q4f16_1-MLC",
- "estimated_vram_bytes": 3980990464,
- "model_id": "internlm2_5-1_8b-chat-q4f16_1-MLC"
- },
- {
- "model": "HF://mlc-ai/gemma-2b-it-q4f16_1-MLC",
- "model_id": "gemma-2b-q4f16_1-MLC",
- "estimated_vram_bytes": 3980990464
- }
- ]
- }
复制代码 3.2 运行打包命令
这一步必要能访问 HuggingFace,可能必要部署署理
3.3 创建署名
- cd /root/android/mlc-llm/android/MLCChat
- /root/android/android-studio/jbr/bin/keytool -genkey -v -keystore my-release-key.jks -keyalg RSA -keysize 2048 -validity 10000
- Enter keystore password:
- Re-enter new password:
- What is your first and last name?
- [Unknown]: Any
- What is the name of your organizational unit?
- [Unknown]: Any
- What is the name of your organization?
- [Unknown]: Any
- What is the name of your City or Locality?
- [Unknown]: Any
- What is the name of your State or Province?
- [Unknown]: Any
- What is the two-letter country code for this unit?
- [Unknown]: CN
- Is CN=Any, OU=Any, O=Any, L=Any, ST=Any, C=CN correct?
- [no]: yes
- Generating 2,048 bit RSA key pair and self-signed certificate (SHA256withRSA) with a validity of 10,000 days
- for: CN=Any, OU=Any, O=Any, L=Any, ST=Any, C=CN
- [Storing my-release-key.jks]
复制代码 3.4 修改 gradle 设置
假如是本地可以 WIFI 或 USB 调试,不用署名;在服务器构建必要署名,修改 app/build.gradle 为如下内容,重要是增加了署名部分,留意确认署名文件的位置。
- plugins {
- id 'com.android.application'
- id 'org.jetbrains.kotlin.android'
- }
- android {
- namespace 'ai.mlc.mlcchat'
- compileSdk 34
- defaultConfig {
- applicationId "ai.mlc.mlcchat"
- minSdk 26
- targetSdk 33
- versionCode 1
- versionName "1.0"
- testInstrumentationRunner "androidx.test.runner.AndroidJUnitRunner"
- vectorDrawables {
- useSupportLibrary true
- }
- }
- compileOptions {
- sourceCompatibility JavaVersion.VERSION_1_8
- targetCompatibility JavaVersion.VERSION_1_8
- }
- kotlinOptions {
- jvmTarget = '1.8'
- }
- buildFeatures {
- compose true
- }
- composeOptions {
- kotlinCompilerExtensionVersion '1.4.3'
- }
- packagingOptions {
- resources {
- excludes += '/META-INF/{AL2.0,LGPL2.1}'
- }
- }
- signingConfigs {
- release {
- storeFile file("/root/android/mlc-llm/android/MLCChat/my-release-key.jks")
- storePassword "123456"
- keyAlias "mykey"
- keyPassword "123456"
- }
- }
- buildTypes {
- release {
- minifyEnabled false
- proguardFiles getDefaultProguardFile('proguard-android-optimize.txt'), 'proguard-rules.pro'
- signingConfig signingConfigs.release
- }
- }
- }
- dependencies {
- implementation project(":mlc4j")
- implementation 'androidx.core:core-ktx:1.10.1'
- implementation 'androidx.lifecycle:lifecycle-runtime-ktx:2.6.1'
- implementation 'androidx.activity:activity-compose:1.7.1'
- implementation platform('androidx.compose:compose-bom:2022.10.00')
- implementation 'androidx.lifecycle:lifecycle-viewmodel-compose:2.6.1'
- implementation 'androidx.compose.ui:ui'
- implementation 'androidx.compose.ui:ui-graphics'
- implementation 'androidx.compose.ui:ui-tooling-preview'
- implementation 'androidx.compose.material3:material3:1.1.0'
- implementation 'androidx.compose.material:material-icons-extended'
- implementation 'androidx.appcompat:appcompat:1.6.1'
- implementation 'androidx.navigation:navigation-compose:2.5.3'
- implementation 'com.google.code.gson:gson:2.10.1'
- implementation fileTree(dir: 'src/main/libs', include: ['
- *.aar', '*
- .jar'], exclude: [])
- testImplementation 'junit:junit:4.13.2'
- androidTestImplementation 'androidx.test.ext:junit:1.1.5'
- androidTestImplementation 'androidx.test.espresso:espresso-core:3.5.1'
- androidTestImplementation platform('androidx.compose:compose-bom:2022.10.00')
- androidTestImplementation 'androidx.compose.ui:ui-test-junit4'
- debugImplementation 'androidx.compose.ui:ui-tooling'
- debugImplementation 'androidx.compose.ui:ui-test-manifest'
- }
复制代码 3.5 命令行编译
运行编译命令,完成后在 app/build/outputs/apk/release 生成 app-release.apk 安装包,下载到手机上运行,运行 App 必要能访问 HuggingFace 下载模型。
- ./gradlew assembleRelease
复制代码
3.6 运行体验
- 运行 App 必要能访问 HuggingFce 下载模型
- 必要大概 4G 运行内存
- 假如运行闪退,很可能是下载不完备可以删除重新下载
免责声明:如果侵犯了您的权益,请联系站长,我们会及时删除侵权内容,谢谢合作!更多信息从访问主页:qidao123.com:ToB企服之家,中国第一个企服评测及商务社交产业平台。 |