Skip to content

AI / llama-android

Go to a project
Commit fe929074 by 王一诺
Options

llama.cpp 项目 实现前端本地模型调用

parents
Expand all
Inline Side-by-side
Showing with 2672 additions and 0 deletions
.gitignore 0 → 100644
*.iml
.gradle
/local.properties
/.idea/caches
/.idea/libraries
/.idea/modules.xml
/.idea/workspace.xml
/.idea/navEditor.xml
/.idea/assetWizardSettings.xml
.DS_Store
/build
/captures
.externalNativeBuild
.cxx
local.properties
.idea/.gitignore 0 → 100644
# Default ignored files
/shelf/
/workspace.xml
.idea/.name 0 → 100644
llama-android
\ No newline at end of file
.idea/compiler.xml 0 → 100644
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
<component name="CompilerConfiguration">
<bytecodeTargetLevel target="17" />
</component>
</project>
\ No newline at end of file
.idea/deploymentTargetSelector.xml 0 → 100644
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
<component name="deploymentTargetSelector">
<selectionStates>
<SelectionState runConfigName="app">
<option name="selectionMode" value="DROPDOWN" />
</SelectionState>
</selectionStates>
</component>
</project>
\ No newline at end of file
.idea/gradle.xml 0 → 100644
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
<component name="GradleMigrationSettings" migrationVersion="1" />
<component name="GradleSettings">
<option name="linkedExternalProjectsSettings">
<GradleProjectSettings>
<option name="externalProjectPath" value="$PROJECT_DIR$" />
<option name="gradleJvm" value="#GRADLE_LOCAL_JAVA_HOME" />
<option name="modules">
<set>
<option value="$PROJECT_DIR$" />
<option value="$PROJECT_DIR$/app" />
<option value="$PROJECT_DIR$/llamalib" />
</set>
</option>
<option name="resolveExternalAnnotations" value="false" />
</GradleProjectSettings>
</option>
</component>
</project>
\ No newline at end of file
.idea/inspectionProfiles/Project_Default.xml 0 → 100644
<component name="InspectionProjectProfileManager">
<profile version="1.0">
<option name="myName" value="Project Default" />
<inspection_tool class="ComposePreviewDimensionRespectsLimit" enabled="true" level="WARNING" enabled_by_default="true">
<option name="composableFile" value="true" />
<option name="previewFile" value="true" />
</inspection_tool>
<inspection_tool class="ComposePreviewMustBeTopLevelFunction" enabled="true" level="ERROR" enabled_by_default="true">
<option name="composableFile" value="true" />
<option name="previewFile" value="true" />
</inspection_tool>
<inspection_tool class="ComposePreviewNeedsComposableAnnotation" enabled="true" level="ERROR" enabled_by_default="true">
<option name="composableFile" value="true" />
<option name="previewFile" value="true" />
</inspection_tool>
<inspection_tool class="ComposePreviewNotSupportedInUnitTestFiles" enabled="true" level="ERROR" enabled_by_default="true">
<option name="composableFile" value="true" />
<option name="previewFile" value="true" />
</inspection_tool>
<inspection_tool class="GlancePreviewDimensionRespectsLimit" enabled="true" level="WARNING" enabled_by_default="true">
<option name="composableFile" value="true" />
</inspection_tool>
<inspection_tool class="GlancePreviewMustBeTopLevelFunction" enabled="true" level="ERROR" enabled_by_default="true">
<option name="composableFile" value="true" />
</inspection_tool>
<inspection_tool class="GlancePreviewNeedsComposableAnnotation" enabled="true" level="ERROR" enabled_by_default="true">
<option name="composableFile" value="true" />
</inspection_tool>
<inspection_tool class="GlancePreviewNotSupportedInUnitTestFiles" enabled="true" level="ERROR" enabled_by_default="true">
<option name="composableFile" value="true" />
</inspection_tool>
<inspection_tool class="PreviewAnnotationInFunctionWithParameters" enabled="true" level="ERROR" enabled_by_default="true">
<option name="composableFile" value="true" />
<option name="previewFile" value="true" />
</inspection_tool>
<inspection_tool class="PreviewApiLevelMustBeValid" enabled="true" level="ERROR" enabled_by_default="true">
<option name="composableFile" value="true" />
<option name="previewFile" value="true" />
</inspection_tool>
<inspection_tool class="PreviewFontScaleMustBeGreaterThanZero" enabled="true" level="ERROR" enabled_by_default="true">
<option name="composableFile" value="true" />
<option name="previewFile" value="true" />
</inspection_tool>
<inspection_tool class="PreviewMultipleParameterProviders" enabled="true" level="ERROR" enabled_by_default="true">
<option name="composableFile" value="true" />
<option name="previewFile" value="true" />
</inspection_tool>
<inspection_tool class="PreviewPickerAnnotation" enabled="true" level="ERROR" enabled_by_default="true">
<option name="composableFile" value="true" />
<option name="previewFile" value="true" />
</inspection_tool>
</profile>
</component>
\ No newline at end of file
.idea/kotlinc.xml 0 → 100644
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
<component name="KotlinJpsPluginSettings">
<option name="version" value="1.9.0" />
</component>
</project>
\ No newline at end of file
.idea/migrations.xml 0 → 100644
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
<component name="ProjectMigrations">
<option name="MigrateToGradleLocalJavaHome">
<set>
<option value="$PROJECT_DIR$" />
</set>
</option>
</component>
</project>
\ No newline at end of file
.idea/misc.xml 0 → 100644
<project version="4">
<component name="ExternalStorageConfigurationManager" enabled="true" />
<component name="ProjectRootManager" version="2" languageLevel="JDK_17" default="true" project-jdk-name="jbr-17" project-jdk-type="JavaSDK">
<output url="file://$PROJECT_DIR$/build/classes" />
</component>
<component name="ProjectType">
<option name="id" value="Android" />
</component>
</project>
\ No newline at end of file
app/.gitignore 0 → 100644
/build
\ No newline at end of file
app/build.gradle 0 → 100644
plugins {
alias(libs.plugins.android.application)
alias(libs.plugins.kotlin.android)
}
android {
namespace 'com.coolook.llama'
compileSdk 35
defaultConfig {
applicationId "com.coolook.llama"
minSdk 26
targetSdk 34
versionCode 1
versionName "1.0"
testInstrumentationRunner "androidx.test.runner.AndroidJUnitRunner"
vectorDrawables {
useSupportLibrary true
}
}
buildTypes {
release {
minifyEnabled false
proguardFiles getDefaultProguardFile('proguard-android-optimize.txt'), 'proguard-rules.pro'
}
}
compileOptions {
sourceCompatibility JavaVersion.VERSION_1_8
targetCompatibility JavaVersion.VERSION_1_8
}
kotlinOptions {
jvmTarget = '1.8'
}
buildFeatures {
compose true
viewBinding true
}
composeOptions {
kotlinCompilerExtensionVersion '1.5.1'
}
packaging {
resources {
excludes += '/META-INF/{AL2.0,LGPL2.1}'
}
}
}
dependencies {
implementation (project(':llamalib'))
implementation libs.androidx.core.ktx
implementation libs.androidx.lifecycle.runtime.ktx
implementation libs.androidx.activity.compose
implementation platform(libs.androidx.compose.bom)
implementation libs.androidx.ui
implementation libs.androidx.ui.graphics
implementation libs.androidx.ui.tooling.preview
implementation libs.androidx.material3
implementation libs.material
implementation libs.androidx.appcompat
implementation libs.androidx.constraintlayout
implementation libs.androidx.navigation.fragment
implementation libs.androidx.navigation.ui
implementation project(':llamalib')
testImplementation libs.junit
androidTestImplementation libs.androidx.junit
androidTestImplementation libs.androidx.espresso.core
androidTestImplementation platform(libs.androidx.compose.bom)
androidTestImplementation libs.androidx.ui.test.junit4
debugImplementation libs.androidx.ui.tooling
debugImplementation libs.androidx.ui.test.manifest
}
\ No newline at end of file
app/proguard-rules.pro 0 → 100644
# Add project specific ProGuard rules here.
# You can control the set of applied configuration files using the
# proguardFiles setting in build.gradle.
#
# For more details, see
# http://developer.android.com/guide/developing/tools/proguard.html
# If your project uses WebView with JS, uncomment the following
# and specify the fully qualified class name to the JavaScript interface
# class:
#-keepclassmembers class fqcn.of.javascript.interface.for.webview {
# public *;
#}
# Uncomment this to preserve the line number information for
# debugging stack traces.
#-keepattributes SourceFile,LineNumberTable
# If you keep the line number information, uncomment this to
# hide the original source file name.
#-renamesourcefileattribute SourceFile
\ No newline at end of file
app/src/androidTest/java/com/coolook/llama/ExampleInstrumentedTest.kt 0 → 100644
package com.coolook.llama
import androidx.test.platform.app.InstrumentationRegistry
import androidx.test.ext.junit.runners.AndroidJUnit4
import org.junit.Test
import org.junit.runner.RunWith
import org.junit.Assert.*
/**
* Instrumented test, which will execute on an Android device.
*
* See [testing documentation](http://d.android.com/tools/testing).
*/
@RunWith(AndroidJUnit4::class)
class ExampleInstrumentedTest {
@Test
fun useAppContext() {
// Context of the app under test.
val appContext = InstrumentationRegistry.getInstrumentation().targetContext
assertEquals("com.coolook.llama", appContext.packageName)
}
}
\ No newline at end of file
app/src/main/AndroidManifest.xml 0 → 100644
<?xml version="1.0" encoding="utf-8"?>
<manifest xmlns:android="http://schemas.android.com/apk/res/android"
xmlns:tools="http://schemas.android.com/tools">
<uses-permission android:name="android.permission.READ_EXTERNAL_STORAGE" />
<application
android:largeHeap="true"
android:allowBackup="true"
android:dataExtractionRules="@xml/data_extraction_rules"
android:fullBackupContent="@xml/backup_rules"
android:icon="@mipmap/ic_launcher"
android:label="@string/app_name"
android:roundIcon="@mipmap/ic_launcher_round"
android:supportsRtl="true"
android:theme="@style/Theme.Llamaandroid"
tools:targetApi="31">
<activity
android:name=".MainActivity"
android:exported="true"
android:label="@string/app_name"
android:theme="@style/Theme.Llamaandroid">
<intent-filter>
<action android:name="android.intent.action.MAIN" />
<category android:name="android.intent.category.LAUNCHER" />
</intent-filter>
</activity>
</application>
</manifest>
\ No newline at end of file
app/src/main/assets/models/distilgpt2_bin/config.json 0 → 100644
{
"_num_labels": 1,
"activation_function": "gelu_new",
"architectures": [
"GPT2LMHeadModel"
],
"attn_pdrop": 0.1,
"bos_token_id": 50256,
"embd_pdrop": 0.1,
"eos_token_id": 50256,
"id2label": {
"0": "LABEL_0"
},
"initializer_range": 0.02,
"label2id": {
"LABEL_0": 0
},
"layer_norm_epsilon": 1e-05,
"model_type": "gpt2",
"n_ctx": 1024,
"n_embd": 768,
"n_head": 12,
"n_inner": null,
"n_layer": 6,
"n_positions": 1024,
"reorder_and_upcast_attn": false,
"resid_pdrop": 0.1,
"scale_attn_by_inverse_layer_idx": false,
"scale_attn_weights": true,
"summary_activation": null,
"summary_first_dropout": 0.1,
"summary_proj_to_labels": true,
"summary_type": "cls_index",
"summary_use_proj": true,
"task_specific_params": {
"text-generation": {
"do_sample": true,
"max_length": 50
}
},
"torch_dtype": "float32",
"transformers_version": "4.51.1",
"use_cache": true,
"vocab_size": 50257
}
app/src/main/assets/models/distilgpt2_bin/generation_config.json 0 → 100644
{
"_from_model_config": true,
"bos_token_id": 50256,
"eos_token_id": 50256,
"transformers_version": "4.51.1"
}
app/src/main/assets/models/distilgpt2_bin/merges.txt 0 → 100644
This diff could not be displayed because it is too large.
app/src/main/assets/models/distilgpt2_bin/model-zhen.gguf 0 → 100644
The file could not be displayed because it is too large.
app/src/main/assets/models/distilgpt2_bin/special_tokens_map.json 0 → 100644
{
"bos_token": "<|endoftext|>",
"eos_token": "<|endoftext|>",
"unk_token": "<|endoftext|>"
}
app/src/main/assets/models/distilgpt2_bin/tokenizer.json 0 → 100644
This diff could not be displayed because it is too large.
app/src/main/assets/models/distilgpt2_bin/tokenizer_config.json 0 → 100644
{
"add_prefix_space": false,
"added_tokens_decoder": {
"50256": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<|endoftext|>",
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"extra_special_tokens": {},
"model_max_length": 1024,
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|endoftext|>"
}
app/src/main/assets/models/distilgpt2_bin/vocab.json 0 → 100644
This diff could not be displayed because it is too large.
app/src/main/java/com/coolook/llama/MainActivity.java 0 → 100644
package com.coolook.llama;
import android.app.Activity;
import android.content.res.AssetManager;
import android.os.Bundle;
import com.coolook.llamalib.LLamaAndroid;
import com.google.android.material.snackbar.Snackbar;
import androidx.appcompat.app.AppCompatActivity;
import android.util.Log;
import android.view.View;
import androidx.navigation.NavController;
import androidx.navigation.Navigation;
import androidx.navigation.ui.AppBarConfiguration;
import androidx.navigation.ui.NavigationUI;
import com.coolook.llama.databinding.ActivityMainBinding;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
public class MainActivity extends Activity {
private AppBarConfiguration appBarConfiguration;
private ActivityMainBinding binding;
private LLamaAndroid llamaAndroid;
@Override
protected void onCreate(Bundle savedInstanceState) {
super.onCreate(savedInstanceState);
binding = ActivityMainBinding.inflate(getLayoutInflater());
setContentView(binding.getRoot());
llamaAndroid = LLamaAndroid.getInstance();
try {
loadModelFromAssets("model-zhen.gguf");
} catch (Exception e) {
throw new RuntimeException(e);
}
llamaAndroid.send("Hello", false, new LLamaAndroid.CompletionCallback() {
@Override
public void onToken(String token) {
// 每个生成的 token 会回调这里，你可以逐步拼接生成的对话内容
Log.d("MainActivity", "Generated token: " + token);
}
@Override
public void onComplete() {
// 当对话生成完成时会回调这里
Log.d("MainActivity", "Dialogue generation completed.");
}
});
}
public void loadModelFromAssets(String modelFileName) throws Exception{
try {
// 获取 AssetManager
AssetManager assetManager = getAssets();
InputStream inputStream = assetManager.open("models/distilgpt2_bin/" + modelFileName);
// 读取模型文件
byte[] modelData = new byte[inputStream.available()];
inputStream.read(modelData);
inputStream.close();
// 将模型数据传递给 JNI
String modelPath = getFilesDir() + "/model.bin";
FileOutputStream fos = new FileOutputStream(modelPath);
fos.write(modelData);
fos.close();
// 加载模型
llamaAndroid.load(modelPath, new Runnable() {
@Override
public void run() {
Log.d("MainActivity", "Model loaded successfully!");
}
}, new LLamaAndroid.ErrorHandler() {
@Override
public void onError(Exception e) {
Log.e("MainActivity", "Error loading model: ", e);
}
});
} catch (IOException e) {
e.printStackTrace();
Log.e("MainActivity", "Error reading model file", e);
}
}
}
\ No newline at end of file
app/src/main/res/drawable/ic_launcher_background.xml 0 → 100644
<?xml version="1.0" encoding="utf-8"?>
<vector xmlns:android="http://schemas.android.com/apk/res/android"
android:height="108dp"
android:width="108dp"
android:viewportHeight="108"
android:viewportWidth="108">
<path
android:fillColor="#3DDC84"
android:pathData="M0,0h108v108h-108z" />
<path
android:fillColor="#00000000"
android:pathData="M9,0L9,108"
android:strokeColor="#33FFFFFF"
android:strokeWidth="0.8" />
<path
android:fillColor="#00000000"
android:pathData="M19,0L19,108"
android:strokeColor="#33FFFFFF"
android:strokeWidth="0.8" />
<path
android:fillColor="#00000000"
android:pathData="M29,0L29,108"
android:strokeColor="#33FFFFFF"
android:strokeWidth="0.8" />
<path
android:fillColor="#00000000"
android:pathData="M39,0L39,108"
android:strokeColor="#33FFFFFF"
android:strokeWidth="0.8" />
<path
android:fillColor="#00000000"
android:pathData="M49,0L49,108"
android:strokeColor="#33FFFFFF"
android:strokeWidth="0.8" />
<path
android:fillColor="#00000000"
android:pathData="M59,0L59,108"
android:strokeColor="#33FFFFFF"
android:strokeWidth="0.8" />
<path
android:fillColor="#00000000"
android:pathData="M69,0L69,108"
android:strokeColor="#33FFFFFF"
android:strokeWidth="0.8" />
<path
android:fillColor="#00000000"
android:pathData="M79,0L79,108"
android:strokeColor="#33FFFFFF"
android:strokeWidth="0.8" />
<path
android:fillColor="#00000000"
android:pathData="M89,0L89,108"
android:strokeColor="#33FFFFFF"
android:strokeWidth="0.8" />
<path
android:fillColor="#00000000"
android:pathData="M99,0L99,108"
android:strokeColor="#33FFFFFF"
android:strokeWidth="0.8" />
<path
android:fillColor="#00000000"
android:pathData="M0,9L108,9"
android:strokeColor="#33FFFFFF"
android:strokeWidth="0.8" />
<path
android:fillColor="#00000000"
android:pathData="M0,19L108,19"
android:strokeColor="#33FFFFFF"
android:strokeWidth="0.8" />
<path
android:fillColor="#00000000"
android:pathData="M0,29L108,29"
android:strokeColor="#33FFFFFF"
android:strokeWidth="0.8" />
<path
android:fillColor="#00000000"
android:pathData="M0,39L108,39"
android:strokeColor="#33FFFFFF"
android:strokeWidth="0.8" />
<path
android:fillColor="#00000000"
android:pathData="M0,49L108,49"
android:strokeColor="#33FFFFFF"
android:strokeWidth="0.8" />
<path
android:fillColor="#00000000"
android:pathData="M0,59L108,59"
android:strokeColor="#33FFFFFF"
android:strokeWidth="0.8" />
<path
android:fillColor="#00000000"
android:pathData="M0,69L108,69"
android:strokeColor="#33FFFFFF"
android:strokeWidth="0.8" />
<path
android:fillColor="#00000000"
android:pathData="M0,79L108,79"
android:strokeColor="#33FFFFFF"
android:strokeWidth="0.8" />
<path
android:fillColor="#00000000"
android:pathData="M0,89L108,89"
android:strokeColor="#33FFFFFF"
android:strokeWidth="0.8" />
<path
android:fillColor="#00000000"
android:pathData="M0,99L108,99"
android:strokeColor="#33FFFFFF"
android:strokeWidth="0.8" />
<path
android:fillColor="#00000000"
android:pathData="M19,29L89,29"
android:strokeColor="#33FFFFFF"
android:strokeWidth="0.8" />
<path
android:fillColor="#00000000"
android:pathData="M19,39L89,39"
android:strokeColor="#33FFFFFF"
android:strokeWidth="0.8" />
<path
android:fillColor="#00000000"
android:pathData="M19,49L89,49"
android:strokeColor="#33FFFFFF"
android:strokeWidth="0.8" />
<path
android:fillColor="#00000000"
android:pathData="M19,59L89,59"
android:strokeColor="#33FFFFFF"
android:strokeWidth="0.8" />
<path
android:fillColor="#00000000"
android:pathData="M19,69L89,69"
android:strokeColor="#33FFFFFF"
android:strokeWidth="0.8" />
<path
android:fillColor="#00000000"
android:pathData="M19,79L89,79"
android:strokeColor="#33FFFFFF"
android:strokeWidth="0.8" />
<path
android:fillColor="#00000000"
android:pathData="M29,19L29,89"
android:strokeColor="#33FFFFFF"
android:strokeWidth="0.8" />
<path
android:fillColor="#00000000"
android:pathData="M39,19L39,89"
android:strokeColor="#33FFFFFF"
android:strokeWidth="0.8" />
<path
android:fillColor="#00000000"
android:pathData="M49,19L49,89"
android:strokeColor="#33FFFFFF"
android:strokeWidth="0.8" />
<path
android:fillColor="#00000000"
android:pathData="M59,19L59,89"
android:strokeColor="#33FFFFFF"
android:strokeWidth="0.8" />
<path
android:fillColor="#00000000"
android:pathData="M69,19L69,89"
android:strokeColor="#33FFFFFF"
android:strokeWidth="0.8" />
<path
android:fillColor="#00000000"
android:pathData="M79,19L79,89"
android:strokeColor="#33FFFFFF"
android:strokeWidth="0.8" />
</vector>
app/src/main/res/drawable/ic_launcher_foreground.xml 0 → 100644
<vector xmlns:android="http://schemas.android.com/apk/res/android"
xmlns:aapt="http://schemas.android.com/aapt"
android:width="108dp"
android:height="108dp"
android:viewportWidth="108"
android:viewportHeight="108">
<path android:pathData="M31,63.928c0,0 6.4,-11 12.1,-13.1c7.2,-2.6 26,-1.4 26,-1.4l38.1,38.1L107,108.928l-32,-1L31,63.928z">
<aapt:attr name="android:fillColor">
<gradient
android:startY="49.59793"
android:startX="42.9492"
android:endY="92.4963"
android:endX="85.84757"
android:type="linear">
<item
android:color="#44000000"
android:offset="0.0" />
<item
android:color="#00000000"
android:offset="1.0" />
</gradient>
</aapt:attr>
</path>
<path
android:pathData="M65.3,45.828l3.8,-6.6c0.2,-0.4 0.1,-0.9 -0.3,-1.1c-0.4,-0.2 -0.9,-0.1 -1.1,0.3l-3.9,6.7c-6.3,-2.8 -13.4,-2.8 -19.7,0l-3.9,-6.7c-0.2,-0.4 -0.7,-0.5 -1.1,-0.3C38.8,38.328 38.7,38.828 38.9,39.228l3.8,6.6C36.2,49.428 31.7,56.028 31,63.928h46C76.3,56.028 71.8,49.428 65.3,45.828zM43.4,57.328c-0.8,0 -1.5,-0.5 -1.8,-1.2c-0.3,-0.7 -0.1,-1.5 0.4,-2.1c0.5,-0.5 1.4,-0.7 2.1,-0.4c0.7,0.3 1.2,1 1.2,1.8C45.3,56.528 44.5,57.328 43.4,57.328L43.4,57.328zM64.6,57.328c-0.8,0 -1.5,-0.5 -1.8,-1.2s-0.1,-1.5 0.4,-2.1c0.5,-0.5 1.4,-0.7 2.1,-0.4c0.7,0.3 1.2,1 1.2,1.8C66.5,56.528 65.6,57.328 64.6,57.328L64.6,57.328z"
android:fillColor="#FFFFFF"
android:fillType="nonZero"
android:strokeWidth="1"
android:strokeColor="#00000000" />
</vector>
\ No newline at end of file
app/src/main/res/layout/activity_main.xml 0 → 100644
<?xml version="1.0" encoding="utf-8"?>
<androidx.coordinatorlayout.widget.CoordinatorLayout xmlns:android="http://schemas.android.com/apk/res/android"
xmlns:app="http://schemas.android.com/apk/res-auto"
xmlns:tools="http://schemas.android.com/tools"
android:layout_width="match_parent"
android:layout_height="match_parent"
android:fitsSystemWindows="true"
tools:context=".MainActivity">
<com.google.android.material.appbar.AppBarLayout
android:layout_height="wrap_content"
android:layout_width="match_parent"
android:fitsSystemWindows="true">
<com.google.android.material.appbar.MaterialToolbar
android:id="@+id/toolbar"
android:layout_width="match_parent"
android:layout_height="?attr/actionBarSize" />
</com.google.android.material.appbar.AppBarLayout>
<com.google.android.material.floatingactionbutton.FloatingActionButton
android:id="@+id/fab"
android:layout_width="wrap_content"
android:layout_height="wrap_content"
android:layout_gravity="bottom|end"
android:layout_marginEnd="@dimen/fab_margin"
android:layout_marginBottom="16dp"
app:srcCompat="@android:drawable/ic_dialog_email" />
</androidx.coordinatorlayout.widget.CoordinatorLayout>
\ No newline at end of file
app/src/main/res/mipmap-anydpi/ic_launcher.xml 0 → 100644
<?xml version="1.0" encoding="utf-8"?>
<adaptive-icon xmlns:android="http://schemas.android.com/apk/res/android">
<background android:drawable="@drawable/ic_launcher_background" />
<foreground android:drawable="@drawable/ic_launcher_foreground" />
<monochrome android:drawable="@drawable/ic_launcher_foreground" />
</adaptive-icon>
\ No newline at end of file
app/src/main/res/mipmap-anydpi/ic_launcher_round.xml 0 → 100644
<?xml version="1.0" encoding="utf-8"?>
<adaptive-icon xmlns:android="http://schemas.android.com/apk/res/android">
<background android:drawable="@drawable/ic_launcher_background" />
<foreground android:drawable="@drawable/ic_launcher_foreground" />
<monochrome android:drawable="@drawable/ic_launcher_foreground" />
</adaptive-icon>
\ No newline at end of file
app/src/main/res/navigation/nav_graph.xml 0 → 100644
<?xml version="1.0" encoding="utf-8"?>
<navigation xmlns:android="http://schemas.android.com/apk/res/android"
xmlns:app="http://schemas.android.com/apk/res-auto"
xmlns:tools="http://schemas.android.com/tools"
android:id="@+id/nav_graph"
app:startDestination="@id/FirstFragment">
<fragment
android:id="@+id/FirstFragment"
android:name="com.coolook.llama.FirstFragment"
android:label="@string/first_fragment_label"
tools:layout="@layout/fragment_first">
<action
android:id="@+id/action_FirstFragment_to_SecondFragment"
app:destination="@id/SecondFragment" />
</fragment>
<fragment
android:id="@+id/SecondFragment"
android:name="com.coolook.llama.SecondFragment"
android:label="@string/second_fragment_label"
tools:layout="@layout/fragment_second">
<action
android:id="@+id/action_SecondFragment_to_FirstFragment"
app:destination="@id/FirstFragment" />
</fragment>
</navigation>
\ No newline at end of file
app/src/main/res/values-land/dimens.xml 0 → 100644
<resources>
<dimen name="fab_margin">48dp</dimen>
</resources>
\ No newline at end of file
app/src/main/res/values-night/themes.xml 0 → 100644
<resources xmlns:tools="http://schemas.android.com/tools">
<!-- Base application theme. -->
<style name="Base.Theme.Llamaandroid" parent="Theme.Material3.DayNight.NoActionBar">
<!-- Customize your dark theme here. -->
<!-- <item name="colorPrimary">@color/my_dark_primary</item> -->
</style>
</resources>
\ No newline at end of file
app/src/main/res/values-v23/themes.xml 0 → 100644
<resources xmlns:tools="http://schemas.android.com/tools">
<style name="Theme.Llamaandroid" parent="Base.Theme.Llamaandroid">
<!-- Transparent system bars for edge-to-edge. -->
<item name="android:navigationBarColor">@android:color/transparent</item>
<item name="android:statusBarColor">@android:color/transparent</item>
<item name="android:windowLightStatusBar">?attr/isLightTheme</item>
</style>
</resources>
\ No newline at end of file
app/src/main/res/values-w1240dp/dimens.xml 0 → 100644
<resources>
<dimen name="fab_margin">200dp</dimen>
</resources>
\ No newline at end of file
app/src/main/res/values-w600dp/dimens.xml 0 → 100644
<resources>
<dimen name="fab_margin">48dp</dimen>
</resources>
\ No newline at end of file
app/src/main/res/values/colors.xml 0 → 100644
<?xml version="1.0" encoding="utf-8"?>
<resources>
<color name="purple_200">#FFBB86FC</color>
<color name="purple_500">#FF6200EE</color>
<color name="purple_700">#FF3700B3</color>
<color name="teal_200">#FF03DAC5</color>
<color name="teal_700">#FF018786</color>
<color name="black">#FF000000</color>
<color name="white">#FFFFFFFF</color>
</resources>
\ No newline at end of file
app/src/main/res/values/dimens.xml 0 → 100644
<resources>
<dimen name="fab_margin">16dp</dimen>
</resources>
\ No newline at end of file
app/src/main/res/values/strings.xml 0 → 100644
<resources>
<string name="app_name">llama-android</string>
<!-- Strings used for fragments for navigation -->
<string name="first_fragment_label">First Fragment</string>
<string name="second_fragment_label">Second Fragment</string>
<string name="next">Next</string>
<string name="previous">Previous</string>
<string name="lorem_ipsum">
Lorem ipsum dolor sit amet, consectetur adipiscing elit. Nam in scelerisque sem. Mauris
volutpat, dolor id interdum ullamcorper, risus dolor egestas lectus, sit amet mattis purus
dui nec risus. Maecenas non sodales nisi, vel dictum dolor. Class aptent taciti sociosqu ad
litora torquent per conubia nostra, per inceptos himenaeos. Suspendisse blandit eleifend
diam, vel rutrum tellus vulputate quis. Aliquam eget libero aliquet, imperdiet nisl a,
ornare ex. Sed rhoncus est ut libero porta lobortis. Fusce in dictum tellus.\n\n
Suspendisse interdum ornare ante. Aliquam nec cursus lorem. Morbi id magna felis. Vivamus
egestas, est a condimentum egestas, turpis nisl iaculis ipsum, in dictum tellus dolor sed
neque. Morbi tellus erat, dapibus ut sem a, iaculis tincidunt dui. Interdum et malesuada
fames ac ante ipsum primis in faucibus. Curabitur et eros porttitor, ultricies urna vitae,
molestie nibh. Phasellus at commodo eros, non aliquet metus. Sed maximus nisl nec dolor
bibendum, vel congue leo egestas.\n\n
Sed interdum tortor nibh, in sagittis risus mollis quis. Curabitur mi odio, condimentum sit
amet auctor at, mollis non turpis. Nullam pretium libero vestibulum, finibus orci vel,
molestie quam. Fusce blandit tincidunt nulla, quis sollicitudin libero facilisis et. Integer
interdum nunc ligula, et fermentum metus hendrerit id. Vestibulum lectus felis, dictum at
lacinia sit amet, tristique id quam. Cras eu consequat dui. Suspendisse sodales nunc ligula,
in lobortis sem porta sed. Integer id ultrices magna, in luctus elit. Sed a pellentesque
est.\n\n
Aenean nunc velit, lacinia sed dolor sed, ultrices viverra nulla. Etiam a venenatis nibh.
Morbi laoreet, tortor sed facilisis varius, nibh orci rhoncus nulla, id elementum leo dui
non lorem. Nam mollis ipsum quis auctor varius. Quisque elementum eu libero sed commodo. In
eros nisl, imperdiet vel imperdiet et, scelerisque a mauris. Pellentesque varius ex nunc,
quis imperdiet eros placerat ac. Duis finibus orci et est auctor tincidunt. Sed non viverra
ipsum. Nunc quis augue egestas, cursus lorem at, molestie sem. Morbi a consectetur ipsum, a
placerat diam. Etiam vulputate dignissim convallis. Integer faucibus mauris sit amet finibus
convallis.\n\n
Phasellus in aliquet mi. Pellentesque habitant morbi tristique senectus et netus et
malesuada fames ac turpis egestas. In volutpat arcu ut felis sagittis, in finibus massa
gravida. Pellentesque id tellus orci. Integer dictum, lorem sed efficitur ullamcorper,
libero justo consectetur ipsum, in mollis nisl ex sed nisl. Donec maximus ullamcorper
sodales. Praesent bibendum rhoncus tellus nec feugiat. In a ornare nulla. Donec rhoncus
libero vel nunc consequat, quis tincidunt nisl eleifend. Cras bibendum enim a justo luctus
vestibulum. Fusce dictum libero quis erat maximus, vitae volutpat diam dignissim.
</string>
</resources>
\ No newline at end of file
app/src/main/res/values/themes.xml 0 → 100644
<?xml version="1.0" encoding="utf-8"?>
<resources>
<style name="Theme.Llamaandroid" parent="android:Theme.Material.Light.NoActionBar" />
<!-- Base application theme. -->
<style name="Base.Theme.Llamaandroid" parent="Theme.Material3.DayNight.NoActionBar">
<!-- Customize your light theme here. -->
<!-- <item name="colorPrimary">@color/my_light_primary</item> -->
</style>
</resources>
\ No newline at end of file
app/src/main/res/xml/backup_rules.xml 0 → 100644
<?xml version="1.0" encoding="utf-8"?><!--
Sample backup rules file; uncomment and customize as necessary.
See https://developer.android.com/guide/topics/data/autobackup
for details.
Note: This file is ignored for devices older that API 31
See https://developer.android.com/about/versions/12/backup-restore
-->
<full-backup-content>
<!--
<include domain="sharedpref" path="."/>
<exclude domain="sharedpref" path="device.xml"/>
-->
</full-backup-content>
\ No newline at end of file
app/src/main/res/xml/data_extraction_rules.xml 0 → 100644
<?xml version="1.0" encoding="utf-8"?><!--
Sample data extraction rules file; uncomment and customize as necessary.
See https://developer.android.com/about/versions/12/backup-restore#xml-changes
for details.
-->
<data-extraction-rules>
<cloud-backup>
<!-- TODO: Use <include> and <exclude> to control what is backed up.
<include .../>
<exclude .../>
-->
</cloud-backup>
<!--
<device-transfer>
<include .../>
<exclude .../>
</device-transfer>
-->
</data-extraction-rules>
\ No newline at end of file
app/src/test/java/com/coolook/llama/ExampleUnitTest.kt 0 → 100644
package com.coolook.llama
import org.junit.Test
import org.junit.Assert.*
/**
* Example local unit test, which will execute on the development machine (host).
*
* See [testing documentation](http://d.android.com/tools/testing).
*/
class ExampleUnitTest {
@Test
fun addition_isCorrect() {
assertEquals(4, 2 + 2)
}
}
\ No newline at end of file
build.gradle 0 → 100644
// Top-level build file where you can add configuration options common to all sub-projects/modules.
plugins {
alias(libs.plugins.android.application) apply false
alias(libs.plugins.kotlin.android) apply false
alias(libs.plugins.android.library) apply false
}
\ No newline at end of file
gradle.properties 0 → 100644
# Project-wide Gradle settings.
# IDE (e.g. Android Studio) users:
# Gradle settings configured through the IDE *will override*
# any settings specified in this file.
# For more details on how to configure your build environment visit
# http://www.gradle.org/docs/current/userguide/build_environment.html
# Specifies the JVM arguments used for the daemon process.
# The setting is particularly useful for tweaking memory settings.
org.gradle.jvmargs=-Xmx4g -Dfile.encoding=UTF-8
# When configured, Gradle will run in incubating parallel mode.
# This option should only be used with decoupled projects. For more details, visit
# https://developer.android.com/r/tools/gradle-multi-project-decoupled-projects
# org.gradle.parallel=true
# AndroidX package structure to make it clearer which packages are bundled with the
# Android operating system, and which are packaged with your app's APK
# https://developer.android.com/topic/libraries/support-library/androidx-rn
android.useAndroidX=true
# Kotlin code style for this project: "official" or "obsolete":
kotlin.code.style=official
# Enables namespacing of each library's R class so that its R class includes only the
# resources declared in the library itself and none from the library's dependencies,
# thereby reducing the size of the R class for that library
android.nonTransitiveRClass=true
\ No newline at end of file
gradle/libs.versions.toml 0 → 100644
[versions]
agp = "8.6.0"
kotlin = "1.9.0"
coreKtx = "1.15.0"
junit = "4.13.2"
junitVersion = "1.2.1"
espressoCore = "3.6.1"
lifecycleRuntimeKtx = "2.8.7"
activityCompose = "1.10.1"
composeBom = "2024.04.01"
material = "1.12.0"
appcompat = "1.7.0"
constraintlayout = "2.2.1"
navigationFragment = "2.6.0"
navigationUi = "2.6.0"
[libraries]
androidx-core-ktx = { group = "androidx.core", name = "core-ktx", version.ref = "coreKtx" }
junit = { group = "junit", name = "junit", version.ref = "junit" }
androidx-junit = { group = "androidx.test.ext", name = "junit", version.ref = "junitVersion" }
androidx-espresso-core = { group = "androidx.test.espresso", name = "espresso-core", version.ref = "espressoCore" }
androidx-lifecycle-runtime-ktx = { group = "androidx.lifecycle", name = "lifecycle-runtime-ktx", version.ref = "lifecycleRuntimeKtx" }
androidx-activity-compose = { group = "androidx.activity", name = "activity-compose", version.ref = "activityCompose" }
androidx-compose-bom = { group = "androidx.compose", name = "compose-bom", version.ref = "composeBom" }
androidx-ui = { group = "androidx.compose.ui", name = "ui" }
androidx-ui-graphics = { group = "androidx.compose.ui", name = "ui-graphics" }
androidx-ui-tooling = { group = "androidx.compose.ui", name = "ui-tooling" }
androidx-ui-tooling-preview = { group = "androidx.compose.ui", name = "ui-tooling-preview" }
androidx-ui-test-manifest = { group = "androidx.compose.ui", name = "ui-test-manifest" }
androidx-ui-test-junit4 = { group = "androidx.compose.ui", name = "ui-test-junit4" }
androidx-material3 = { group = "androidx.compose.material3", name = "material3" }
material = { group = "com.google.android.material", name = "material", version.ref = "material" }
androidx-appcompat = { group = "androidx.appcompat", name = "appcompat", version.ref = "appcompat" }
androidx-constraintlayout = { group = "androidx.constraintlayout", name = "constraintlayout", version.ref = "constraintlayout" }
androidx-navigation-fragment = { group = "androidx.navigation", name = "navigation-fragment", version.ref = "navigationFragment" }
androidx-navigation-ui = { group = "androidx.navigation", name = "navigation-ui", version.ref = "navigationUi" }
[plugins]
android-application = { id = "com.android.application", version.ref = "agp" }
kotlin-android = { id = "org.jetbrains.kotlin.android", version.ref = "kotlin" }
android-library = { id = "com.android.library", version.ref = "agp" }
gradle/wrapper/gradle-wrapper.jar 0 → 100644
No preview for this file type
gradle/wrapper/gradle-wrapper.properties 0 → 100644
#Wed Apr 09 11:52:39 CST 2025
distributionBase=GRADLE_USER_HOME
distributionPath=wrapper/dists
distributionUrl=https\://services.gradle.org/distributions/gradle-8.7-bin.zip
zipStoreBase=GRADLE_USER_HOME
zipStorePath=wrapper/dists
gradlew 0 → 100755
#!/usr/bin/env sh
#
# Copyright 2015 the original author or authors.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# https://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
##############################################################################
##
## Gradle start up script for UN*X
##
##############################################################################
# Attempt to set APP_HOME
# Resolve links: $0 may be a link
PRG="$0"
# Need this for relative symlinks.
while [ -h "$PRG" ] ; do
ls=`ls -ld "$PRG"`
link=`expr "$ls" : '.*-> \(.*\)$'`
if expr "$link" : '/.*' > /dev/null; then
PRG="$link"
else
PRG=`dirname "$PRG"`"/$link"
fi
done
SAVED="`pwd`"
cd "`dirname \"$PRG\"`/" >/dev/null
APP_HOME="`pwd -P`"
cd "$SAVED" >/dev/null
APP_NAME="Gradle"
APP_BASE_NAME=`basename "$0"`
# Add default JVM options here. You can also use JAVA_OPTS and GRADLE_OPTS to pass JVM options to this script.
DEFAULT_JVM_OPTS='"-Xmx64m" "-Xms64m"'
# Use the maximum available, or set MAX_FD != -1 to use that value.
MAX_FD="maximum"
warn () {
echo "$*"
}
die () {
echo
echo "$*"
echo
exit 1
}
# OS specific support (must be 'true' or 'false').
cygwin=false
msys=false
darwin=false
nonstop=false
case "`uname`" in
CYGWIN* )
cygwin=true
;;
Darwin* )
darwin=true
;;
MINGW* )
msys=true
;;
NONSTOP* )
nonstop=true
;;
esac
CLASSPATH=$APP_HOME/gradle/wrapper/gradle-wrapper.jar
# Determine the Java command to use to start the JVM.
if [ -n "$JAVA_HOME" ] ; then
if [ -x "$JAVA_HOME/jre/sh/java" ] ; then
# IBM's JDK on AIX uses strange locations for the executables
JAVACMD="$JAVA_HOME/jre/sh/java"
else
JAVACMD="$JAVA_HOME/bin/java"
fi
if [ ! -x "$JAVACMD" ] ; then
die "ERROR: JAVA_HOME is set to an invalid directory: $JAVA_HOME
Please set the JAVA_HOME variable in your environment to match the
location of your Java installation."
fi
else
JAVACMD="java"
which java >/dev/null 2>&1 || die "ERROR: JAVA_HOME is not set and no 'java' command could be found in your PATH.
Please set the JAVA_HOME variable in your environment to match the
location of your Java installation."
fi
# Increase the maximum file descriptors if we can.
if [ "$cygwin" = "false" -a "$darwin" = "false" -a "$nonstop" = "false" ] ; then
MAX_FD_LIMIT=`ulimit -H -n`
if [ $? -eq 0 ] ; then
if [ "$MAX_FD" = "maximum" -o "$MAX_FD" = "max" ] ; then
MAX_FD="$MAX_FD_LIMIT"
fi
ulimit -n $MAX_FD
if [ $? -ne 0 ] ; then
warn "Could not set maximum file descriptor limit: $MAX_FD"
fi
else
warn "Could not query maximum file descriptor limit: $MAX_FD_LIMIT"
fi
fi
# For Darwin, add options to specify how the application appears in the dock
if $darwin; then
GRADLE_OPTS="$GRADLE_OPTS \"-Xdock:name=$APP_NAME\" \"-Xdock:icon=$APP_HOME/media/gradle.icns\""
fi
# For Cygwin or MSYS, switch paths to Windows format before running java
if [ "$cygwin" = "true" -o "$msys" = "true" ] ; then
APP_HOME=`cygpath --path --mixed "$APP_HOME"`
CLASSPATH=`cygpath --path --mixed "$CLASSPATH"`
JAVACMD=`cygpath --unix "$JAVACMD"`
# We build the pattern for arguments to be converted via cygpath
ROOTDIRSRAW=`find -L / -maxdepth 1 -mindepth 1 -type d 2>/dev/null`
SEP=""
for dir in $ROOTDIRSRAW ; do
ROOTDIRS="$ROOTDIRS$SEP$dir"
SEP="|"
done
OURCYGPATTERN="(^($ROOTDIRS))"
# Add a user-defined pattern to the cygpath arguments
if [ "$GRADLE_CYGPATTERN" != "" ] ; then
OURCYGPATTERN="$OURCYGPATTERN|($GRADLE_CYGPATTERN)"
fi
# Now convert the arguments - kludge to limit ourselves to /bin/sh
i=0
for arg in "$@" ; do
CHECK=`echo "$arg"|egrep -c "$OURCYGPATTERN" -`
CHECK2=`echo "$arg"|egrep -c "^-"` ### Determine if an option
if [ $CHECK -ne 0 ] && [ $CHECK2 -eq 0 ] ; then ### Added a condition
eval `echo args$i`=`cygpath --path --ignore --mixed "$arg"`
else
eval `echo args$i`="\"$arg\""
fi
i=`expr $i + 1`
done
case $i in
0) set -- ;;
1) set -- "$args0" ;;
2) set -- "$args0" "$args1" ;;
3) set -- "$args0" "$args1" "$args2" ;;
4) set -- "$args0" "$args1" "$args2" "$args3" ;;
5) set -- "$args0" "$args1" "$args2" "$args3" "$args4" ;;
6) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" ;;
7) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" ;;
8) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" "$args7" ;;
9) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" "$args7" "$args8" ;;
esac
fi
# Escape application args
save () {
for i do printf %s\\n "$i" | sed "s/'/'\\\\''/g;1s/^/'/;\$s/\$/' \\\\/" ; done
echo " "
}
APP_ARGS=`save "$@"`
# Collect all arguments for the java command, following the shell quoting and substitution rules
eval set -- $DEFAULT_JVM_OPTS $JAVA_OPTS $GRADLE_OPTS "\"-Dorg.gradle.appname=$APP_BASE_NAME\"" -classpath "\"$CLASSPATH\"" org.gradle.wrapper.GradleWrapperMain "$APP_ARGS"
exec "$JAVACMD" "$@"
gradlew.bat 0 → 100644
@rem
@rem Copyright 2015 the original author or authors.
@rem
@rem Licensed under the Apache License, Version 2.0 (the "License");
@rem you may not use this file except in compliance with the License.
@rem You may obtain a copy of the License at
@rem
@rem https://www.apache.org/licenses/LICENSE-2.0
@rem
@rem Unless required by applicable law or agreed to in writing, software
@rem distributed under the License is distributed on an "AS IS" BASIS,
@rem WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
@rem See the License for the specific language governing permissions and
@rem limitations under the License.
@rem
@if "%DEBUG%" == "" @echo off
@rem ##########################################################################
@rem
@rem Gradle startup script for Windows
@rem
@rem ##########################################################################
@rem Set local scope for the variables with windows NT shell
if "%OS%"=="Windows_NT" setlocal
set DIRNAME=%~dp0
if "%DIRNAME%" == "" set DIRNAME=.
set APP_BASE_NAME=%~n0
set APP_HOME=%DIRNAME%
@rem Resolve any "." and ".." in APP_HOME to make it shorter.
for %%i in ("%APP_HOME%") do set APP_HOME=%%~fi
@rem Add default JVM options here. You can also use JAVA_OPTS and GRADLE_OPTS to pass JVM options to this script.
set DEFAULT_JVM_OPTS="-Xmx64m" "-Xms64m"
@rem Find java.exe
if defined JAVA_HOME goto findJavaFromJavaHome
set JAVA_EXE=java.exe
%JAVA_EXE% -version >NUL 2>&1
if "%ERRORLEVEL%" == "0" goto execute
echo.
echo ERROR: JAVA_HOME is not set and no 'java' command could be found in your PATH.
echo.
echo Please set the JAVA_HOME variable in your environment to match the
echo location of your Java installation.
goto fail
:findJavaFromJavaHome
set JAVA_HOME=%JAVA_HOME:"=%
set JAVA_EXE=%JAVA_HOME%/bin/java.exe
if exist "%JAVA_EXE%" goto execute
echo.
echo ERROR: JAVA_HOME is set to an invalid directory: %JAVA_HOME%
echo.
echo Please set the JAVA_HOME variable in your environment to match the
echo location of your Java installation.
goto fail
:execute
@rem Setup the command line
set CLASSPATH=%APP_HOME%\gradle\wrapper\gradle-wrapper.jar
@rem Execute Gradle
"%JAVA_EXE%" %DEFAULT_JVM_OPTS% %JAVA_OPTS% %GRADLE_OPTS% "-Dorg.gradle.appname=%APP_BASE_NAME%" -classpath "%CLASSPATH%" org.gradle.wrapper.GradleWrapperMain %*
:end
@rem End local scope for the variables with windows NT shell
if "%ERRORLEVEL%"=="0" goto mainEnd
:fail
rem Set variable GRADLE_EXIT_CONSOLE if you need the _script_ return code instead of
rem the _cmd.exe /c_ return code!
if not "" == "%GRADLE_EXIT_CONSOLE%" exit 1
exit /b 1
:mainEnd
if "%OS%"=="Windows_NT" endlocal
:omega
llamalib/.gitignore 0 → 100644
/build
\ No newline at end of file
llamalib/build.gradle 0 → 100644
plugins {
alias(libs.plugins.android.library)
}
android {
namespace 'com.coolook.llamalib'
compileSdk 34
defaultConfig {
minSdk 26
testInstrumentationRunner "androidx.test.runner.AndroidJUnitRunner"
consumerProguardFiles "consumer-rules.pro"
externalNativeBuild {
cmake {
// 设置 CMake 参数
arguments "-DLLAMA_CURL=OFF",
"-DLLAMA_BUILD_COMMON=ON",
"-DGGML_LLAMAFILE=OFF",
"-DCMAKE_BUILD_TYPE=Release"
// 设置 C++ 编译标志
cppFlags "-std=c++17"
// 如果需要传递空参数
// arguments ""
// cppFlags ""
}
}
}
buildTypes {
release {
minifyEnabled false
proguardFiles getDefaultProguardFile('proguard-android-optimize.txt'), 'proguard-rules.pro'
}
}
compileOptions {
sourceCompatibility JavaVersion.VERSION_1_8
targetCompatibility JavaVersion.VERSION_1_8
}
externalNativeBuild {
cmake {
path "src/main/cpp/CMakeLists.txt"
version "3.22.1"
}
}
}
dependencies {
implementation libs.androidx.appcompat
implementation libs.material
testImplementation libs.junit
androidTestImplementation libs.androidx.junit
androidTestImplementation libs.androidx.espresso.core
}
\ No newline at end of file
llamalib/proguard-rules.pro 0 → 100644
# Add project specific ProGuard rules here.
# You can control the set of applied configuration files using the
# proguardFiles setting in build.gradle.
#
# For more details, see
# http://developer.android.com/guide/developing/tools/proguard.html
# If your project uses WebView with JS, uncomment the following
# and specify the fully qualified class name to the JavaScript interface
# class:
#-keepclassmembers class fqcn.of.javascript.interface.for.webview {
# public *;
#}
# Uncomment this to preserve the line number information for
# debugging stack traces.
#-keepattributes SourceFile,LineNumberTable
# If you keep the line number information, uncomment this to
# hide the original source file name.
#-renamesourcefileattribute SourceFile
\ No newline at end of file
llamalib/src/androidTest/java/com/coolook/llamalib/ExampleInstrumentedTest.java 0 → 100644
package com.coolook.llamalib;
import android.content.Context;
import androidx.test.platform.app.InstrumentationRegistry;
import androidx.test.ext.junit.runners.AndroidJUnit4;
import org.junit.Test;
import org.junit.runner.RunWith;
import static org.junit.Assert.*;
/**
* Instrumented test, which will execute on an Android device.
*
* @see <a href="http://d.android.com/tools/testing">Testing documentation</a>
*/
@RunWith(AndroidJUnit4.class)
public class ExampleInstrumentedTest {
@Test
public void useAppContext() {
// Context of the app under test.
Context appContext = InstrumentationRegistry.getInstrumentation().getTargetContext();
assertEquals("com.coolook.llamalib.test", appContext.getPackageName());
}
}
\ No newline at end of file
llamalib/src/main/AndroidManifest.xml 0 → 100644
<?xml version="1.0" encoding="utf-8"?>
<manifest xmlns:android="http://schemas.android.com/apk/res/android">
</manifest>
\ No newline at end of file
llamalib/src/main/cpp/CMakeLists.txt 0 → 100644
# For more information about using CMake with Android Studio, read the
# documentation: https://d.android.com/studio/projects/add-native-code.html.
# For more examples on how to use CMake, see https://github.com/android/ndk-samples.
# Sets the minimum CMake version required for this project.
cmake_minimum_required(VERSION 3.22.1)
# Declares the project name. The project name can be accessed via ${ PROJECT_NAME},
# Since this is the top level CMakeLists.txt, the project name is also accessible
# with ${CMAKE_PROJECT_NAME} (both CMake variables are in-sync within the top level
# build script scope).
project("llama-android")
#include(FetchContent)
#FetchContent_Declare(
# llama
# GIT_REPOSITORY https://github.com/ggml-org/llama.cpp
# GIT_TAG master
#)
# Also provides "common"
#FetchContent_MakeAvailable(llama)
# Creates and names a library, sets it as either STATIC
# or SHARED, and provides the relative paths to its source code.
# You can define multiple libraries, and CMake builds them for you.
# Gradle automatically packages shared libraries with your APK.
#
# In this top level CMakeLists.txt, ${CMAKE_PROJECT_NAME} is used to define
# the target library name; in the sub-module's CMakeLists.txt, ${PROJECT_NAME}
# is preferred for the same purpose.
#
#load local llama.cpp
add_subdirectory(llama-cpp build-llama)
# In order to load a library into your app from Java/Kotlin, you must call
# System.loadLibrary() and pass the name of the library defined here;
# for GameActivity/NativeActivity derived applications, the same library name must be
# used in the AndroidManifest.xml file.
add_library(${CMAKE_PROJECT_NAME} SHARED
# List C/C++ source files with relative paths to this CMakeLists.txt.
llama-android.cpp)
# Specifies libraries CMake should link to your target library. You
# can link libraries from various origins, such as libraries defined in this
# build script, prebuilt third-party libraries, or Android system libraries.
target_link_libraries(${CMAKE_PROJECT_NAME}
# List libraries link to the target library
llama
common
android
log)
llamalib/src/main/cpp/llama-cpp/CMakeLists.txt 0 → 100644
cmake_minimum_required(VERSION 3.14) # for add_link_options and implicit target directories.
project("llama.cpp" C CXX)
include(CheckIncludeFileCXX)
#set(CMAKE_WARN_DEPRECATED YES)
set(CMAKE_WARN_UNUSED_CLI YES)
set(CMAKE_EXPORT_COMPILE_COMMANDS ON)
if (NOT XCODE AND NOT MSVC AND NOT CMAKE_BUILD_TYPE)
set(CMAKE_BUILD_TYPE Release CACHE STRING "Build type" FORCE)
set_property(CACHE CMAKE_BUILD_TYPE PROPERTY STRINGS "Debug" "Release" "MinSizeRel" "RelWithDebInfo")
endif()
# Add path to modules
list(APPEND CMAKE_MODULE_PATH "${CMAKE_CURRENT_SOURCE_DIR}/cmake/")
set(CMAKE_RUNTIME_OUTPUT_DIRECTORY ${CMAKE_BINARY_DIR}/bin)
set(CMAKE_LIBRARY_OUTPUT_DIRECTORY ${CMAKE_BINARY_DIR}/bin)
if (CMAKE_SOURCE_DIR STREQUAL CMAKE_CURRENT_SOURCE_DIR)
set(LLAMA_STANDALONE ON)
include(git-vars)
# configure project version
# TODO
else()
set(LLAMA_STANDALONE OFF)
endif()
option(LLAMA_USE_SYSTEM_GGML "Use system libggml" OFF)
if (EMSCRIPTEN)
set(BUILD_SHARED_LIBS_DEFAULT OFF)
option(LLAMA_WASM_SINGLE_FILE "llama: embed WASM inside the generated llama.js" ON)
else()
if (MINGW)
set(BUILD_SHARED_LIBS_DEFAULT OFF)
else()
set(BUILD_SHARED_LIBS_DEFAULT ON)
endif()
endif()
option(BUILD_SHARED_LIBS "build shared libraries" ${BUILD_SHARED_LIBS_DEFAULT})
if (WIN32)
add_compile_definitions(_CRT_SECURE_NO_WARNINGS)
endif()
if (MSVC)
add_compile_options("$<$<COMPILE_LANGUAGE:C>:/utf-8>")
add_compile_options("$<$<COMPILE_LANGUAGE:CXX>:/utf-8>")
add_compile_options("$<$<COMPILE_LANGUAGE:C>:/bigobj>")
add_compile_options("$<$<COMPILE_LANGUAGE:CXX>:/bigobj>")
endif()
#
# option list
#
# debug
option(LLAMA_ALL_WARNINGS "llama: enable all compiler warnings" ON)
option(LLAMA_ALL_WARNINGS_3RD_PARTY "llama: enable all compiler warnings in 3rd party libs" OFF)
# build
option(LLAMA_FATAL_WARNINGS "llama: enable -Werror flag" OFF)
# sanitizers
option(LLAMA_SANITIZE_THREAD "llama: enable thread sanitizer" OFF)
option(LLAMA_SANITIZE_ADDRESS "llama: enable address sanitizer" OFF)
option(LLAMA_SANITIZE_UNDEFINED "llama: enable undefined sanitizer" OFF)
# utils
option(LLAMA_BUILD_COMMON "llama: build common utils library" ${LLAMA_STANDALONE})
# extra artifacts
option(LLAMA_BUILD_TESTS "llama: build tests" ${LLAMA_STANDALONE})
option(LLAMA_BUILD_EXAMPLES "llama: build examples" ${LLAMA_STANDALONE})
option(LLAMA_BUILD_SERVER "llama: build server example" ${LLAMA_STANDALONE})
# 3rd party libs
option(LLAMA_CURL "llama: use libcurl to download model from an URL" ON)
option(LLAMA_LLGUIDANCE "llama-common: include LLGuidance library for structured output in common utils" OFF)
# Required for relocatable CMake package
include(${CMAKE_CURRENT_SOURCE_DIR}/cmake/build-info.cmake)
include(${CMAKE_CURRENT_SOURCE_DIR}/cmake/common.cmake)
# override ggml options
set(GGML_ALL_WARNINGS ${LLAMA_ALL_WARNINGS})
set(GGML_FATAL_WARNINGS ${LLAMA_FATAL_WARNINGS})
# change the default for these ggml options
if (NOT DEFINED GGML_LLAMAFILE)
set(GGML_LLAMAFILE_DEFAULT ON)
endif()
if (NOT DEFINED GGML_CUDA_GRAPHS)
set(GGML_CUDA_GRAPHS_DEFAULT ON)
endif()
# transition helpers
function (llama_option_depr TYPE OLD NEW)
if (${OLD})
message(${TYPE} "${OLD} is deprecated and will be removed in the future.\nUse ${NEW} instead\n")
set(${NEW} ON PARENT_SCOPE)
endif()
endfunction()
llama_option_depr(FATAL_ERROR LLAMA_CUBLAS GGML_CUDA)
llama_option_depr(WARNING LLAMA_CUDA GGML_CUDA)
llama_option_depr(WARNING LLAMA_KOMPUTE GGML_KOMPUTE)
llama_option_depr(WARNING LLAMA_METAL GGML_METAL)
llama_option_depr(WARNING LLAMA_METAL_EMBED_LIBRARY GGML_METAL_EMBED_LIBRARY)
llama_option_depr(WARNING LLAMA_NATIVE GGML_NATIVE)
llama_option_depr(WARNING LLAMA_RPC GGML_RPC)
llama_option_depr(WARNING LLAMA_SYCL GGML_SYCL)
llama_option_depr(WARNING LLAMA_SYCL_F16 GGML_SYCL_F16)
llama_option_depr(WARNING LLAMA_CANN GGML_CANN)
if (NOT MSVC)
if (LLAMA_SANITIZE_THREAD)
message(STATUS "Using -fsanitize=thread")
add_compile_options(-fsanitize=thread)
link_libraries (-fsanitize=thread)
endif()
if (LLAMA_SANITIZE_ADDRESS)
message(STATUS "Using -fsanitize=address")
add_compile_options(-fsanitize=address -fno-omit-frame-pointer)
link_libraries (-fsanitize=address)
endif()
if (LLAMA_SANITIZE_UNDEFINED)
message(STATUS "Using -fsanitize=undefined")
add_compile_options(-fsanitize=undefined)
link_libraries (-fsanitize=undefined)
endif()
endif()
#
# 3rd-party
#
if (LLAMA_USE_SYSTEM_GGML)
message(STATUS "Using system-provided libggml, skipping ggml build")
find_package(ggml REQUIRED)
add_library(ggml ALIAS ggml::ggml)
endif()
if (NOT TARGET ggml AND NOT LLAMA_USE_SYSTEM_GGML)
add_subdirectory(ggml)
# ... otherwise assume ggml is added by a parent CMakeLists.txt
endif()
#
# build the library
#
add_subdirectory(src)
#
# utils, programs, examples and tests
#
if (NOT LLAMA_BUILD_COMMON)
message(STATUS "LLAMA_BUILD_COMMON is OFF, disabling LLAMA_CURL")
set(LLAMA_CURL OFF)
endif()
if (LLAMA_BUILD_COMMON)
add_subdirectory(common)
endif()
if (LLAMA_BUILD_COMMON AND LLAMA_BUILD_TESTS AND NOT CMAKE_JS_VERSION)
include(CTest)
add_subdirectory(tests)
endif()
if (LLAMA_BUILD_COMMON AND LLAMA_BUILD_EXAMPLES)
add_subdirectory(examples)
add_subdirectory(pocs)
endif()
#
# install
#
include(GNUInstallDirs)
include(CMakePackageConfigHelpers)
set(LLAMA_BUILD_NUMBER ${BUILD_NUMBER})
set(LLAMA_BUILD_COMMIT ${BUILD_COMMIT})
set(LLAMA_INSTALL_VERSION 0.0.${BUILD_NUMBER})
set(LLAMA_INCLUDE_INSTALL_DIR ${CMAKE_INSTALL_INCLUDEDIR} CACHE PATH "Location of header files")
set(LLAMA_LIB_INSTALL_DIR ${CMAKE_INSTALL_LIBDIR} CACHE PATH "Location of library files")
set(LLAMA_BIN_INSTALL_DIR ${CMAKE_INSTALL_BINDIR} CACHE PATH "Location of binary files")
set(LLAMA_PUBLIC_HEADERS
${CMAKE_CURRENT_SOURCE_DIR}/include/llama.h
${CMAKE_CURRENT_SOURCE_DIR}/include/llama-cpp.h)
set_target_properties(llama
PROPERTIES
PUBLIC_HEADER "${LLAMA_PUBLIC_HEADERS}")
install(TARGETS llama LIBRARY PUBLIC_HEADER)
configure_package_config_file(
${CMAKE_CURRENT_SOURCE_DIR}/cmake/llama-config.cmake.in
${CMAKE_CURRENT_BINARY_DIR}/llama-config.cmake
INSTALL_DESTINATION ${CMAKE_INSTALL_LIBDIR}/cmake/llama
PATH_VARS LLAMA_INCLUDE_INSTALL_DIR
LLAMA_LIB_INSTALL_DIR
LLAMA_BIN_INSTALL_DIR )
write_basic_package_version_file(
${CMAKE_CURRENT_BINARY_DIR}/llama-version.cmake
VERSION ${LLAMA_INSTALL_VERSION}
COMPATIBILITY SameMajorVersion)
install(FILES ${CMAKE_CURRENT_BINARY_DIR}/llama-config.cmake
${CMAKE_CURRENT_BINARY_DIR}/llama-version.cmake
DESTINATION ${CMAKE_INSTALL_LIBDIR}/cmake/llama)
install(
FILES convert_hf_to_gguf.py
PERMISSIONS
OWNER_READ
OWNER_WRITE
OWNER_EXECUTE
GROUP_READ
GROUP_EXECUTE
WORLD_READ
WORLD_EXECUTE
DESTINATION ${CMAKE_INSTALL_BINDIR})
configure_file(cmake/llama.pc.in
"${CMAKE_CURRENT_BINARY_DIR}/llama.pc"
@ONLY)
install(FILES "${CMAKE_CURRENT_BINARY_DIR}/llama.pc"
DESTINATION ${CMAKE_INSTALL_LIBDIR}/pkgconfig)
#
# copy the license files
#
# Check if running in GitHub Actions
if(DEFINED ENV{GITHUB_ACTIONS} AND "$ENV{GITHUB_ACTIONS}" STREQUAL "true")
message(STATUS "Running inside GitHub Actions - copying license files")
# Copy all files from licenses/ to build/bin/
file(GLOB LICENSE_FILES "${CMAKE_SOURCE_DIR}/licenses/*")
foreach(LICENSE_FILE ${LICENSE_FILES})
get_filename_component(FILENAME ${LICENSE_FILE} NAME)
configure_file(${LICENSE_FILE} "${CMAKE_BINARY_DIR}/bin/${FILENAME}" COPYONLY)
endforeach()
endif()
llamalib/src/main/cpp/llama-cpp/CMakePresets.json 0 → 100644
{
"version": 4,
"configurePresets": [
{
"name": "base",
"hidden": true,
"generator": "Ninja",
"binaryDir": "${sourceDir}/build-${presetName}",
"cacheVariables": {
"CMAKE_EXPORT_COMPILE_COMMANDS": "ON",
"CMAKE_INSTALL_RPATH": "$ORIGIN;$ORIGIN/.."
}
},
{
"name": "sycl-base",
"hidden": true,
"generator": "Ninja",
"binaryDir": "${sourceDir}/build-${presetName}",
"cacheVariables": {
"CMAKE_EXPORT_COMPILE_COMMANDS": "ON",
"CMAKE_CXX_COMPILER": "icx",
"CMAKE_C_COMPILER": "cl",
"GGML_SYCL": "ON",
"CMAKE_INSTALL_RPATH": "$ORIGIN;$ORIGIN/.."
}
},
{ "name": "debug", "hidden": true, "cacheVariables": { "CMAKE_BUILD_TYPE": "Debug" } },
{ "name": "release", "hidden": true, "cacheVariables": { "CMAKE_BUILD_TYPE": "Release" } },
{ "name": "reldbg", "hidden": true, "cacheVariables": { "CMAKE_BUILD_TYPE": "RelWithDebInfo" } },
{ "name": "static", "hidden": true, "cacheVariables": { "GGML_STATIC": "ON" } },
{ "name": "sycl_f16", "hidden": true, "cacheVariables": { "GGML_SYCL_F16": "ON" } },
{ "name": "vulkan", "hidden": true, "cacheVariables": { "GGML_VULKAN": "ON" } },
{
"name": "x64-windows-llvm", "hidden": true,
"cacheVariables": {
"CMAKE_TOOLCHAIN_FILE": "${sourceDir}/cmake/x64-windows-llvm.cmake"
}
},
{
"name": "arm64-windows-msvc", "hidden": true,
"architecture": { "value": "arm64", "strategy": "external" },
"toolset": { "value": "host=x64", "strategy": "external" },
"cacheVariables": {
"CMAKE_TOOLCHAIN_FILE": "${sourceDir}/cmake/arm64-windows-msvc.cmake"
}
},
{
"name": "arm64-windows-llvm", "hidden": true,
"architecture": { "value": "arm64", "strategy": "external" },
"toolset": { "value": "host=x64", "strategy": "external" },
"cacheVariables": {
"CMAKE_TOOLCHAIN_FILE": "${sourceDir}/cmake/arm64-windows-llvm.cmake"
}
},
{
"name": "arm64-apple-clang", "hidden": true,
"architecture": { "value": "arm64", "strategy": "external" },
"toolset": { "value": "host=x64", "strategy": "external" },
"cacheVariables": {
"CMAKE_TOOLCHAIN_FILE": "${sourceDir}/cmake/arm64-apple-clang.cmake"
}
},
{ "name": "arm64-windows-llvm-debug", "inherits": [ "base", "arm64-windows-llvm", "debug" ] },
{ "name": "arm64-windows-llvm-release", "inherits": [ "base", "arm64-windows-llvm", "reldbg" ] },
{ "name": "arm64-windows-llvm+static-release", "inherits": [ "base", "arm64-windows-llvm", "reldbg", "static" ] },
{ "name": "arm64-apple-clang-debug", "inherits": [ "base", "arm64-apple-clang", "debug" ] },
{ "name": "arm64-apple-clang-release", "inherits": [ "base", "arm64-apple-clang", "reldbg" ] },
{ "name": "arm64-apple-clang+static-release", "inherits": [ "base", "arm64-apple-clang", "reldbg", "static" ] },
{ "name": "arm64-windows-msvc-debug", "inherits": [ "base", "arm64-windows-msvc", "debug" ] },
{ "name": "arm64-windows-msvc-release", "inherits": [ "base", "arm64-windows-msvc", "reldbg" ] },
{ "name": "arm64-windows-msvc+static-release", "inherits": [ "base", "arm64-windows-msvc", "reldbg", "static" ] },
{ "name": "x64-windows-llvm-debug", "inherits": [ "base", "x64-windows-llvm", "debug" ] },
{ "name": "x64-windows-llvm-release", "inherits": [ "base", "x64-windows-llvm", "release" ] },
{ "name": "x64-windows-llvm-reldbg", "inherits": [ "base", "x64-windows-llvm", "reldbg" ] },
{ "name": "x64-windows-llvm+static-release", "inherits": [ "base", "x64-windows-llvm", "reldbg", "static" ] },
{ "name": "x64-windows-msvc-debug", "inherits": [ "base", "debug" ] },
{ "name": "x64-windows-msvc-release", "inherits": [ "base", "reldbg" ] },
{ "name": "x64-windows-msvc+static-release", "inherits": [ "base", "reldbg", "static" ] },
{ "name": "x64-windows-sycl-debug", "inherits": [ "sycl-base", "debug" ] },
{ "name": "x64-windows-sycl-debug-f16", "inherits": [ "sycl-base", "debug", "sycl_f16" ] },
{ "name": "x64-windows-sycl-release", "inherits": [ "sycl-base", "release" ] },
{ "name": "x64-windows-sycl-release-f16", "inherits": [ "sycl-base", "release", "sycl_f16" ] },
{ "name": "x64-windows-vulkan-debug", "inherits": [ "base", "vulkan", "debug" ] },
{ "name": "x64-windows-vulkan-release", "inherits": [ "base", "vulkan", "release" ] }
]
}
llamalib/src/main/cpp/llama-cpp/CODEOWNERS 0 → 100644
# collaborators can optionally add themselves here to indicate their availability for reviewing related PRs
/ci/ @ggerganov
/.devops/*.Dockerfile @ngxson
/examples/server/ @ngxson
/ggml/src/ggml-cuda/fattn* @JohannesGaessler
/ggml/src/ggml-cuda/mmq.* @JohannesGaessler
/ggml/src/ggml-cuda/mmv.* @JohannesGaessler
/ggml/src/ggml-cuda/mmvq.* @JohannesGaessler
/ggml/src/ggml-opt.cpp @JohannesGaessler
/ggml/src/gguf.cpp @JohannesGaessler
llamalib/src/main/cpp/llama-cpp/CONTRIBUTING.md 0 → 100644
# Pull requests (for contributors)
- llama.cpp uses the ggml tensor library for model evaluation. If you are unfamiliar with ggml, consider taking a look at the [examples in the ggml repository](https://github.com/ggml-org/ggml/tree/master/examples/). [simple](https://github.com/ggml-org/ggml/tree/master/examples/simple) shows the bare minimum for using ggml. [gpt-2](https://github.com/ggml-org/ggml/tree/master/examples/gpt-2) has minimal implementations for language model inference using GPT-2. [mnist](https://github.com/ggml-org/ggml/tree/master/examples/mnist) demonstrates how to train and evaluate a simple image classifier
- Test your changes:
- Execute [the full CI locally on your machine](ci/README.md) before publishing
- Verify that the perplexity and the performance are not affected negatively by your changes (use `llama-perplexity` and `llama-bench`)
- If you modified the `ggml` source, run the `test-backend-ops` tool to check whether different backend implementations of the `ggml` operators produce consistent results (this requires access to at least two different `ggml` backends)
- If you modified a `ggml` operator or added a new one, add the corresponding test cases to `test-backend-ops`
- Create separate PRs for each feature or fix. Avoid combining unrelated changes in a single PR
- Consider allowing write access to your branch for faster reviews, as reviewers can push commits directly
- If your PR becomes stale, don't hesitate to ping the maintainers in the comments
# Pull requests (for collaborators)
- Squash-merge PRs
- Use the following format for the squashed commit title: `<module> : <commit title> (#<issue_number>)`. For example: `utils : fix typo in utils.py (#1234)`
- Optionally pick a `<module>` from here: https://github.com/ggml-org/llama.cpp/wiki/Modules
- Consider adding yourself to [CODEOWNERS](CODEOWNERS)
# Coding guidelines
- Avoid adding third-party dependencies, extra files, extra headers, etc.
- Always consider cross-compatibility with other operating systems and architectures
- Avoid fancy-looking modern STL constructs, use basic `for` loops, avoid templates, keep it simple
- Vertical alignment makes things more readable and easier to batch edit
- Clean-up any trailing whitespaces, use 4 spaces for indentation, brackets on the same line, `void * ptr`, `int & a`
- Use sized integer types such as `int32_t` in the public API, e.g. `size_t` may also be appropriate for allocation sizes or byte offsets
- Declare structs with `struct foo {}` instead of `typedef struct foo {} foo`
- In C++ code omit optional `struct` and `enum` keyword whenever they are not necessary
```cpp
// OK
llama_context * ctx;
const llama_rope_type rope_type;
// not OK
struct llama_context * ctx;
const enum llama_rope_type rope_type;
```
_(NOTE: this guideline is yet to be applied to the `llama.cpp` codebase. New code should follow this guideline.)_
- Try to follow the existing patterns in the code (indentation, spaces, etc.). In case of doubt use `clang-format` (from clang-tools v15+) to format the added code
- For anything not covered in the current guidelines, refer to the [C++ Core Guidelines](https://isocpp.github.io/CppCoreGuidelines/CppCoreGuidelines)
- Tensors store data in row-major order. We refer to dimension 0 as columns, 1 as rows, 2 as matrices
- Matrix multiplication is unconventional: [`C = ggml_mul_mat(ctx, A, B)`](https://github.com/ggml-org/llama.cpp/blob/880e352277fc017df4d5794f0c21c44e1eae2b84/ggml.h#L1058-L1064) means $C^T = A B^T \Leftrightarrow C = B A^T.$
![matmul](media/matmul.png)
# Naming guidelines
- Use `snake_case` for function, variable and type names
- Naming usually optimizes for longest common prefix (see https://github.com/ggml-org/ggml/pull/302#discussion_r1243240963)
```cpp
// not OK
int small_number;
int big_number;
// OK
int number_small;
int number_big;
```
- Enum values are always in upper case and prefixed with the enum name
```cpp
enum llama_vocab_type {
LLAMA_VOCAB_TYPE_NONE = 0,
LLAMA_VOCAB_TYPE_SPM = 1,
LLAMA_VOCAB_TYPE_BPE = 2,
LLAMA_VOCAB_TYPE_WPM = 3,
LLAMA_VOCAB_TYPE_UGM = 4,
LLAMA_VOCAB_TYPE_RWKV = 5,
};
```
- The general naming pattern is `<class>_<method>`, with `<method>` being `<action>_<noun>`
```cpp
llama_model_init(); // class: "llama_model", method: "init"
llama_sampler_chain_remove(); // class: "llama_sampler_chain", method: "remove"
llama_sampler_get_seed(); // class: "llama_sampler", method: "get_seed"
llama_set_embeddings(); // class: "llama_context", method: "set_embeddings"
llama_n_threads(); // class: "llama_context", method: "n_threads"
llama_adapter_lora_free(); // class: "llama_adapter_lora", method: "free"
```
- The `get` `<action>` can be omitted
- The `<noun>` can be omitted if not necessary
- The `_context` suffix of the `<class>` is optional. Use it to disambiguate symbols when needed
- Use `init`/`free` for constructor/destructor `<action>`
- Use the `_t` suffix when a type is supposed to be opaque to the user - it's not relevant to them if it is a struct or anything else
```cpp
typedef struct llama_context * llama_context_t;
enum llama_pooling_type llama_pooling_type(const llama_context_t ctx);
```
_(NOTE: this guideline is yet to be applied to the `llama.cpp` codebase. New code should follow this guideline)_
- C/C++ filenames are all lowercase with dashes. Headers use the `.h` extension. Source files use the `.c` or `.cpp` extension
- Python filenames are all lowercase with underscores
- _(TODO: abbreviations usage)_
# Preprocessor directives
- _(TODO: add guidelines with examples and apply them to the codebase)_
```cpp
#ifdef FOO
#endif // FOO
```
# Documentation
- Documentation is a community effort
- When you need to look into the source code to figure out how to use an API consider adding a short summary to the header file for future reference
- When you notice incorrect or outdated documentation, please update it
# Resources
The Github issues, PRs and discussions contain a lot of information that can be useful to get familiar with the codebase. For convenience, some of the more important information is referenced from Github projects:
https://github.com/ggml-org/llama.cpp/projects
llamalib/src/main/cpp/llama-cpp/LICENSE 0 → 100644
MIT License
Copyright (c) 2023-2024 The ggml authors
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.
llamalib/src/main/cpp/llama-cpp/SECURITY.md 0 → 100644
# Security Policy
- [**Using llama.cpp securely**](#using-llamacpp-securely)
- [Untrusted models](#untrusted-models)
- [Untrusted inputs](#untrusted-inputs)
- [Data privacy](#data-privacy)
- [Untrusted environments or networks](#untrusted-environments-or-networks)
- [Multi-Tenant environments](#multi-tenant-environments)
- [**Reporting a vulnerability**](#reporting-a-vulnerability)
## Using llama.cpp securely
### Untrusted models
Be careful when running untrusted models. This classification includes models created by unknown developers or utilizing data obtained from unknown sources.
*Always execute untrusted models within a secure, isolated environment such as a sandbox* (e.g., containers, virtual machines). This helps protect your system from potentially malicious code.
> [!NOTE]
> The trustworthiness of a model is not binary. You must always determine the proper level of caution depending on the specific model and how it matches your use case and risk tolerance.
### Untrusted inputs
Some models accept various input formats (text, images, audio, etc.). The libraries converting these inputs have varying security levels, so it's crucial to isolate the model and carefully pre-process inputs to mitigate script injection risks.
For maximum security when handling untrusted inputs, you may need to employ the following:
* Sandboxing: Isolate the environment where the inference happens.
* Pre-analysis: Check how the model performs by default when exposed to prompt injection (e.g. using [fuzzing for prompt injection](https://github.com/FonduAI/awesome-prompt-injection?tab=readme-ov-file#tools)). This will give you leads on how hard you will have to work on the next topics.
* Updates: Keep both LLaMA C++ and your libraries updated with the latest security patches.
* Input Sanitation: Before feeding data to the model, sanitize inputs rigorously. This involves techniques such as:
* Validation: Enforce strict rules on allowed characters and data types.
* Filtering: Remove potentially malicious scripts or code fragments.
* Encoding: Convert special characters into safe representations.
* Verification: Run tooling that identifies potential script injections (e.g. [models that detect prompt injection attempts](https://python.langchain.com/docs/guides/safety/hugging_face_prompt_injection)).
### Data privacy
To protect sensitive data from potential leaks or unauthorized access, it is crucial to sandbox the model execution. This means running the model in a secure, isolated environment, which helps mitigate many attack vectors.
### Untrusted environments or networks
If you can't run your models in a secure and isolated environment or if it must be exposed to an untrusted network, make sure to take the following security precautions:
* Confirm the hash of any downloaded artifact (e.g. pre-trained model weights) matches a known-good value
* Encrypt your data if sending it over the network.
### Multi-Tenant environments
If you intend to run multiple models in parallel with shared memory, it is your responsibility to ensure the models do not interact or access each other's data. The primary areas of concern are tenant isolation, resource allocation, model sharing and hardware attacks.
1. Tenant Isolation: Models should run separately with strong isolation methods to prevent unwanted data access. Separating networks is crucial for isolation, as it prevents unauthorized access to data or models and malicious users from sending graphs to execute under another tenant's identity.
2. Resource Allocation: A denial of service caused by one model can impact the overall system health. Implement safeguards like rate limits, access controls, and health monitoring.
3. Model Sharing: In a multitenant model sharing design, tenants and users must understand the security risks of running code provided by others. Since there are no reliable methods to detect malicious models, sandboxing the model execution is the recommended approach to mitigate the risk.
4. Hardware Attacks: GPUs or TPUs can also be attacked. [Researches](https://scholar.google.com/scholar?q=gpu+side+channel) has shown that side channel attacks on GPUs are possible, which can make data leak from other models or processes running on the same system at the same time.
## Reporting a vulnerability
Beware that none of the topics under [Using llama.cpp securely](#using-llamacpp-securely) are considered vulnerabilities of LLaMA C++.
<!-- normal version -->
However, If you have discovered a security vulnerability in this project, please report it privately. **Do not disclose it as a public issue.** This gives us time to work with you to fix the issue before public exposure, reducing the chance that the exploit will be used before a patch is released.
Please disclose it as a private [security advisory](https://github.com/ggml-org/llama.cpp/security/advisories/new).
A team of volunteers on a reasonable-effort basis maintains this project. As such, please give us at least 90 days to work on a fix before public exposure.
llamalib/src/main/cpp/llama-cpp/ci/README.md 0 → 100644
# CI
In addition to [Github Actions](https://github.com/ggml-org/llama.cpp/actions) `llama.cpp` uses a custom CI framework:
https://github.com/ggml-org/ci
It monitors the `master` branch for new commits and runs the
[ci/run.sh](https://github.com/ggml-org/llama.cpp/blob/master/ci/run.sh) script on dedicated cloud instances. This allows us
to execute heavier workloads compared to just using Github Actions. Also with time, the cloud instances will be scaled
to cover various hardware architectures, including GPU and Apple Silicon instances.
Collaborators can optionally trigger the CI run by adding the `ggml-ci` keyword to their commit message.
Only the branches of this repo are monitored for this keyword.
It is a good practice, before publishing changes to execute the full CI locally on your machine:
```bash
mkdir tmp
# CPU-only build
bash ./ci/run.sh ./tmp/results ./tmp/mnt
# with CUDA support
GG_BUILD_CUDA=1 bash ./ci/run.sh ./tmp/results ./tmp/mnt
# with SYCL support
source /opt/intel/oneapi/setvars.sh
GG_BUILD_SYCL=1 bash ./ci/run.sh ./tmp/results ./tmp/mnt
# with MUSA support
GG_BUILD_MUSA=1 bash ./ci/run.sh ./tmp/results ./tmp/mnt
```
## Running MUSA CI in a Docker Container
Assuming `$PWD` is the root of the `llama.cpp` repository, follow these steps to set up and run MUSA CI in a Docker container:
### 1. Create a local directory to store cached models, configuration files and venv:
```bash
mkdir -p $HOME/llama.cpp/ci-cache
```
### 2. Create a local directory to store CI run results:
```bash
mkdir -p $HOME/llama.cpp/ci-results
```
### 3. Start a Docker container and run the CI:
```bash
docker run --privileged -it \
-v $HOME/llama.cpp/ci-cache:/ci-cache \
-v $HOME/llama.cpp/ci-results:/ci-results \
-v $PWD:/ws -w /ws \
mthreads/musa:rc3.1.1-devel-ubuntu22.04
```
Inside the container, execute the following commands:
```bash
apt update -y && apt install -y bc cmake ccache git python3.10-venv time unzip wget
git config --global --add safe.directory /ws
GG_BUILD_MUSA=1 bash ./ci/run.sh /ci-results /ci-cache
```
This setup ensures that the CI runs within an isolated Docker environment while maintaining cached files and results across runs.
llamalib/src/main/cpp/llama-cpp/cmake/arm64-apple-clang.cmake 0 → 100644
set( CMAKE_SYSTEM_NAME Darwin )
set( CMAKE_SYSTEM_PROCESSOR arm64 )
set( target arm64-apple-darwin-macho )
set( CMAKE_C_COMPILER clang )
set( CMAKE_CXX_COMPILER clang++ )
set( CMAKE_C_COMPILER_TARGET ${target} )
set( CMAKE_CXX_COMPILER_TARGET ${target} )
set( arch_c_flags "-march=armv8.4-a -fvectorize -ffp-model=fast -fno-finite-math-only" )
set( warn_c_flags "-Wno-format -Wno-unused-variable -Wno-unused-function" )
set( CMAKE_C_FLAGS_INIT "${arch_c_flags} ${warn_c_flags}" )
set( CMAKE_CXX_FLAGS_INIT "${arch_c_flags} ${warn_c_flags}" )
llamalib/src/main/cpp/llama-cpp/cmake/arm64-windows-llvm.cmake 0 → 100644
set( CMAKE_SYSTEM_NAME Windows )
set( CMAKE_SYSTEM_PROCESSOR arm64 )
set( target arm64-pc-windows-msvc )
set( CMAKE_C_COMPILER clang )
set( CMAKE_CXX_COMPILER clang++ )
set( CMAKE_C_COMPILER_TARGET ${target} )
set( CMAKE_CXX_COMPILER_TARGET ${target} )
set( arch_c_flags "-march=armv8.7-a -fvectorize -ffp-model=fast -fno-finite-math-only" )
set( warn_c_flags "-Wno-format -Wno-unused-variable -Wno-unused-function -Wno-gnu-zero-variadic-macro-arguments" )
set( CMAKE_C_FLAGS_INIT "${arch_c_flags} ${warn_c_flags}" )
set( CMAKE_CXX_FLAGS_INIT "${arch_c_flags} ${warn_c_flags}" )
llamalib/src/main/cpp/llama-cpp/cmake/arm64-windows-msvc.cmake 0 → 100644
set( CMAKE_SYSTEM_NAME Windows )
set( CMAKE_SYSTEM_PROCESSOR arm64 )
set( target arm64-pc-windows-msvc )
set( CMAKE_C_COMPILER_TARGET ${target} )
set( CMAKE_CXX_COMPILER_TARGET ${target} )
llamalib/src/main/cpp/llama-cpp/cmake/build-info.cmake 0 → 100644
set(BUILD_NUMBER 0)
set(BUILD_COMMIT "unknown")
set(BUILD_COMPILER "unknown")
set(BUILD_TARGET "unknown")
# Look for git
find_package(Git)
if(NOT Git_FOUND)
find_program(GIT_EXECUTABLE NAMES git git.exe)
if(GIT_EXECUTABLE)
set(Git_FOUND TRUE)
message(STATUS "Found Git: ${GIT_EXECUTABLE}")
else()
message(WARNING "Git not found. Build info will not be accurate.")
endif()
endif()
# Get the commit count and hash
if(Git_FOUND)
execute_process(
COMMAND ${GIT_EXECUTABLE} rev-parse --short HEAD
WORKING_DIRECTORY ${CMAKE_CURRENT_SOURCE_DIR}
OUTPUT_VARIABLE HEAD
OUTPUT_STRIP_TRAILING_WHITESPACE
RESULT_VARIABLE RES
)
if (RES EQUAL 0)
set(BUILD_COMMIT ${HEAD})
endif()
execute_process(
COMMAND ${GIT_EXECUTABLE} rev-list --count HEAD
WORKING_DIRECTORY ${CMAKE_CURRENT_SOURCE_DIR}
OUTPUT_VARIABLE COUNT
OUTPUT_STRIP_TRAILING_WHITESPACE
RESULT_VARIABLE RES
)
if (RES EQUAL 0)
set(BUILD_NUMBER ${COUNT})
endif()
endif()
if(MSVC)
set(BUILD_COMPILER "${CMAKE_C_COMPILER_ID} ${CMAKE_C_COMPILER_VERSION}")
set(BUILD_TARGET ${CMAKE_VS_PLATFORM_NAME})
else()
execute_process(
COMMAND sh -c "\"$@\" --version | head -1" _ ${CMAKE_C_COMPILER}
OUTPUT_VARIABLE OUT
OUTPUT_STRIP_TRAILING_WHITESPACE
)
set(BUILD_COMPILER ${OUT})
execute_process(
COMMAND ${CMAKE_C_COMPILER} -dumpmachine
OUTPUT_VARIABLE OUT
OUTPUT_STRIP_TRAILING_WHITESPACE
)
set(BUILD_TARGET ${OUT})
endif()
llamalib/src/main/cpp/llama-cpp/cmake/common.cmake 0 → 100644
include("ggml/cmake/common.cmake")
function(llama_add_compile_flags)
if (LLAMA_FATAL_WARNINGS)
if (CMAKE_CXX_COMPILER_ID MATCHES "GNU" OR CMAKE_CXX_COMPILER_ID MATCHES "Clang")
list(APPEND C_FLAGS -Werror)
list(APPEND CXX_FLAGS -Werror)
elseif (CMAKE_CXX_COMPILER_ID STREQUAL "MSVC")
add_compile_options(/WX)
endif()
endif()
if (LLAMA_ALL_WARNINGS)
if (NOT MSVC)
list(APPEND C_FLAGS -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes
-Werror=implicit-int -Werror=implicit-function-declaration)
list(APPEND CXX_FLAGS -Wmissing-declarations -Wmissing-noreturn)
list(APPEND WARNING_FLAGS -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function)
list(APPEND C_FLAGS ${WARNING_FLAGS})
list(APPEND CXX_FLAGS ${WARNING_FLAGS})
ggml_get_flags(${CMAKE_CXX_COMPILER_ID} ${CMAKE_CXX_COMPILER_VERSION})
add_compile_options("$<$<COMPILE_LANGUAGE:C>:${C_FLAGS};${GF_C_FLAGS}>"
"$<$<COMPILE_LANGUAGE:CXX>:${CXX_FLAGS};${GF_CXX_FLAGS}>")
else()
# todo : msvc
set(C_FLAGS "" PARENT_SCOPE)
set(CXX_FLAGS "" PARENT_SCOPE)
endif()
endif()
endfunction()
llamalib/src/main/cpp/llama-cpp/cmake/git-vars.cmake 0 → 100644
find_package(Git)
# the commit's SHA1
execute_process(COMMAND
"${GIT_EXECUTABLE}" describe --match=NeVeRmAtCh --always --abbrev=8
WORKING_DIRECTORY "${CMAKE_SOURCE_DIR}"
OUTPUT_VARIABLE GIT_SHA1
ERROR_QUIET OUTPUT_STRIP_TRAILING_WHITESPACE)
# the date of the commit
execute_process(COMMAND
"${GIT_EXECUTABLE}" log -1 --format=%ad --date=local
WORKING_DIRECTORY "${CMAKE_SOURCE_DIR}"
OUTPUT_VARIABLE GIT_DATE
ERROR_QUIET OUTPUT_STRIP_TRAILING_WHITESPACE)
# the subject of the commit
execute_process(COMMAND
"${GIT_EXECUTABLE}" log -1 --format=%s
WORKING_DIRECTORY "${CMAKE_SOURCE_DIR}"
OUTPUT_VARIABLE GIT_COMMIT_SUBJECT
ERROR_QUIET OUTPUT_STRIP_TRAILING_WHITESPACE)
llamalib/src/main/cpp/llama-cpp/cmake/llama-config.cmake.in 0 → 100644
set(LLAMA_VERSION @LLAMA_INSTALL_VERSION@)
set(LLAMA_BUILD_COMMIT @LLAMA_BUILD_COMMIT@)
set(LLAMA_BUILD_NUMBER @LLAMA_BUILD_NUMBER@)
set(LLAMA_SHARED_LIB @BUILD_SHARED_LIBS@)
@PACKAGE_INIT@
set_and_check(LLAMA_INCLUDE_DIR "@PACKAGE_LLAMA_INCLUDE_INSTALL_DIR@")
set_and_check(LLAMA_LIB_DIR "@PACKAGE_LLAMA_LIB_INSTALL_DIR@")
set_and_check(LLAMA_BIN_DIR "@PACKAGE_LLAMA_BIN_INSTALL_DIR@")
find_package(ggml REQUIRED HINTS ${LLAMA_LIB_DIR}/cmake)
find_library(llama_LIBRARY llama
REQUIRED
HINTS ${LLAMA_LIB_DIR}
NO_CMAKE_FIND_ROOT_PATH
)
add_library(llama UNKNOWN IMPORTED)
set_target_properties(llama
PROPERTIES
INTERFACE_INCLUDE_DIRECTORIES "${LLAMA_INCLUDE_DIR}"
INTERFACE_LINK_LIBRARIES "ggml::ggml;ggml::ggml-base;"
IMPORTED_LINK_INTERFACE_LANGUAGES "CXX"
IMPORTED_LOCATION "${llama_LIBRARY}"
INTERFACE_COMPILE_FEATURES c_std_90
POSITION_INDEPENDENT_CODE ON)
check_required_components(Llama)
llamalib/src/main/cpp/llama-cpp/cmake/llama.pc.in 0 → 100644
prefix=@CMAKE_INSTALL_PREFIX@
exec_prefix=@CMAKE_INSTALL_PREFIX@
libdir=@CMAKE_INSTALL_FULL_LIBDIR@
includedir=@CMAKE_INSTALL_FULL_INCLUDEDIR@
Name: llama
Description: Port of Facebook's LLaMA model in C/C++
Version: @LLAMA_INSTALL_VERSION@
Libs: -L${libdir} -lggml -lggml-base -lllama
Cflags: -I${includedir}
llamalib/src/main/cpp/llama-cpp/cmake/x64-windows-llvm.cmake 0 → 100644
set( CMAKE_SYSTEM_NAME Windows )
set( CMAKE_SYSTEM_PROCESSOR x86_64 )
set( CMAKE_C_COMPILER clang )
set( CMAKE_CXX_COMPILER clang++ )
set( arch_c_flags "-march=native" )
set( CMAKE_C_FLAGS_INIT "${arch_c_flags}" )
set( CMAKE_CXX_FLAGS_INIT "${arch_c_flags}" )
llamalib/src/main/cpp/llama-cpp/common/CMakeLists.txt 0 → 100644
# common
find_package(Threads REQUIRED)
llama_add_compile_flags()
# Build info header
#
if(EXISTS "${CMAKE_CURRENT_SOURCE_DIR}/../.git")
set(GIT_DIR "${CMAKE_CURRENT_SOURCE_DIR}/../.git")
# Is git submodule
if(NOT IS_DIRECTORY "${GIT_DIR}")
file(READ ${GIT_DIR} REAL_GIT_DIR_LINK)
string(REGEX REPLACE "gitdir: (.*)\n$" "\\1" REAL_GIT_DIR ${REAL_GIT_DIR_LINK})
string(FIND "${REAL_GIT_DIR}" "/" SLASH_POS)
if (SLASH_POS EQUAL 0)
set(GIT_DIR "${REAL_GIT_DIR}")
else()
set(GIT_DIR "${CMAKE_CURRENT_SOURCE_DIR}/../${REAL_GIT_DIR}")
endif()
endif()
if(EXISTS "${GIT_DIR}/index")
set(GIT_INDEX "${GIT_DIR}/index")
else()
message(WARNING "Git index not found in git repository.")
set(GIT_INDEX "")
endif()
else()
message(WARNING "Git repository not found; to enable automatic generation of build info, make sure Git is installed and the project is a Git repository.")
set(GIT_INDEX "")
endif()
# Add a custom command to rebuild build-info.cpp when .git/index changes
add_custom_command(
OUTPUT "${CMAKE_CURRENT_SOURCE_DIR}/build-info.cpp"
COMMENT "Generating build details from Git"
COMMAND ${CMAKE_COMMAND} -DMSVC=${MSVC} -DCMAKE_C_COMPILER_VERSION=${CMAKE_C_COMPILER_VERSION}
-DCMAKE_C_COMPILER_ID=${CMAKE_C_COMPILER_ID} -DCMAKE_VS_PLATFORM_NAME=${CMAKE_VS_PLATFORM_NAME}
-DCMAKE_C_COMPILER=${CMAKE_C_COMPILER} -P "${CMAKE_CURRENT_SOURCE_DIR}/cmake/build-info-gen-cpp.cmake"
WORKING_DIRECTORY "${CMAKE_CURRENT_SOURCE_DIR}/.."
DEPENDS "${CMAKE_CURRENT_SOURCE_DIR}/build-info.cpp.in" ${GIT_INDEX}
VERBATIM
)
set(TARGET build_info)
add_library(${TARGET} OBJECT build-info.cpp)
if (BUILD_SHARED_LIBS)
set_target_properties(${TARGET} PROPERTIES POSITION_INDEPENDENT_CODE ON)
endif()
set(TARGET common)
add_library(${TARGET} STATIC
arg.cpp
arg.h
base64.hpp
chat.cpp
chat.h
common.cpp
common.h
console.cpp
console.h
json-schema-to-grammar.cpp
json.hpp
llguidance.cpp
log.cpp
log.h
minja/chat-template.hpp
minja/minja.hpp
ngram-cache.cpp
ngram-cache.h
sampling.cpp
sampling.h
speculative.cpp
speculative.h
)
if (BUILD_SHARED_LIBS)
set_target_properties(${TARGET} PROPERTIES POSITION_INDEPENDENT_CODE ON)
endif()
set(LLAMA_COMMON_EXTRA_LIBS build_info)
# Use curl to download model url
if (LLAMA_CURL)
find_package(CURL)
if (NOT CURL_FOUND)
message(FATAL_ERROR "Could NOT find CURL. Hint: to disable this feature, set -DLLAMA_CURL=OFF")
endif()
target_compile_definitions(${TARGET} PUBLIC LLAMA_USE_CURL)
include_directories(${CURL_INCLUDE_DIRS})
find_library(CURL_LIBRARY curl REQUIRED)
set(LLAMA_COMMON_EXTRA_LIBS ${LLAMA_COMMON_EXTRA_LIBS} ${CURL_LIBRARY})
endif ()
if (LLAMA_LLGUIDANCE)
include(ExternalProject)
set(LLGUIDANCE_SRC ${CMAKE_BINARY_DIR}/llguidance/source)
set(LLGUIDANCE_PATH ${LLGUIDANCE_SRC}/target/release)
# Set the correct library file extension based on platform
if (WIN32)
set(LLGUIDANCE_LIB_NAME "llguidance.lib")
# Add Windows-specific libraries
set(LLGUIDANCE_PLATFORM_LIBS
ws2_32 # Windows Sockets API
userenv # For GetUserProfileDirectoryW
ntdll # For NT functions
bcrypt # For BCryptGenRandom
)
else()
set(LLGUIDANCE_LIB_NAME "libllguidance.a")
set(LLGUIDANCE_PLATFORM_LIBS "")
endif()
ExternalProject_Add(llguidance_ext
GIT_REPOSITORY https://github.com/guidance-ai/llguidance
# v0.7.10:
GIT_TAG 0309d2a6bf40abda35344a362edc71e06d5009f8
PREFIX ${CMAKE_BINARY_DIR}/llguidance
SOURCE_DIR ${LLGUIDANCE_SRC}
BUILD_IN_SOURCE TRUE
CONFIGURE_COMMAND ""
BUILD_COMMAND cargo build --release
INSTALL_COMMAND ""
BUILD_BYPRODUCTS ${LLGUIDANCE_PATH}/${LLGUIDANCE_LIB_NAME} ${LLGUIDANCE_PATH}/llguidance.h
UPDATE_COMMAND ""
)
target_compile_definitions(${TARGET} PUBLIC LLAMA_USE_LLGUIDANCE)
add_library(llguidance STATIC IMPORTED)
set_target_properties(llguidance PROPERTIES IMPORTED_LOCATION ${LLGUIDANCE_PATH}/${LLGUIDANCE_LIB_NAME})
add_dependencies(llguidance llguidance_ext)
target_include_directories(${TARGET} PRIVATE ${LLGUIDANCE_PATH})
# Add platform libraries to the main target
set(LLAMA_COMMON_EXTRA_LIBS ${LLAMA_COMMON_EXTRA_LIBS} llguidance ${LLGUIDANCE_PLATFORM_LIBS})
endif ()
target_include_directories(${TARGET} PUBLIC .)
target_compile_features (${TARGET} PUBLIC cxx_std_17)
target_link_libraries (${TARGET} PRIVATE ${LLAMA_COMMON_EXTRA_LIBS} PUBLIC llama Threads::Threads)
llamalib/src/main/cpp/llama-cpp/common/arg.cpp 0 → 100644
This diff could not be displayed because it is too large.
llamalib/src/main/cpp/llama-cpp/common/arg.h 0 → 100644
#pragma once
#include "common.h"
#include <set>
#include <string>
#include <vector>
//
// CLI argument parsing
//
struct common_arg {
std::set<enum llama_example> examples = {LLAMA_EXAMPLE_COMMON};
std::set<enum llama_example> excludes = {};
std::vector<const char *> args;
const char * value_hint = nullptr; // help text or example for arg value
const char * value_hint_2 = nullptr; // for second arg value
const char * env = nullptr;
std::string help;
bool is_sparam = false; // is current arg a sampling param?
void (*handler_void) (common_params & params) = nullptr;
void (*handler_string) (common_params & params, const std::string &) = nullptr;
void (*handler_str_str)(common_params & params, const std::string &, const std::string &) = nullptr;
void (*handler_int) (common_params & params, int) = nullptr;
common_arg(
const std::initializer_list<const char *> & args,
const char * value_hint,
const std::string & help,
void (*handler)(common_params & params, const std::string &)
) : args(args), value_hint(value_hint), help(help), handler_string(handler) {}
common_arg(
const std::initializer_list<const char *> & args,
const char * value_hint,
const std::string & help,
void (*handler)(common_params & params, int)
) : args(args), value_hint(value_hint), help(help), handler_int(handler) {}
common_arg(
const std::initializer_list<const char *> & args,
const std::string & help,
void (*handler)(common_params & params)
) : args(args), help(help), handler_void(handler) {}
// support 2 values for arg
common_arg(
const std::initializer_list<const char *> & args,
const char * value_hint,
const char * value_hint_2,
const std::string & help,
void (*handler)(common_params & params, const std::string &, const std::string &)
) : args(args), value_hint(value_hint), value_hint_2(value_hint_2), help(help), handler_str_str(handler) {}
common_arg & set_examples(std::initializer_list<enum llama_example> examples);
common_arg & set_excludes(std::initializer_list<enum llama_example> excludes);
common_arg & set_env(const char * env);
common_arg & set_sparam();
bool in_example(enum llama_example ex);
bool is_exclude(enum llama_example ex);
bool get_value_from_env(std::string & output);
bool has_value_from_env();
std::string to_string();
};
struct common_params_context {
enum llama_example ex = LLAMA_EXAMPLE_COMMON;
common_params & params;
std::vector<common_arg> options;
void(*print_usage)(int, char **) = nullptr;
common_params_context(common_params & params) : params(params) {}
};
// parse input arguments from CLI
// if one argument has invalid value, it will automatically display usage of the specific argument (and not the full usage message)
bool common_params_parse(int argc, char ** argv, common_params & params, llama_example ex, void(*print_usage)(int, char **) = nullptr);
// function to be used by test-arg-parser
common_params_context common_params_parser_init(common_params & params, llama_example ex, void(*print_usage)(int, char **) = nullptr);
llamalib/src/main/cpp/llama-cpp/common/build-info.cpp 0 → 100644
int LLAMA_BUILD_NUMBER = 0;
char const *LLAMA_COMMIT = "unknown";
char const *LLAMA_COMPILER = "Android (10552028, +pgo, +bolt, +lto, -mlgo, based on r487747d) clang version 17.0.2 (https://android.googlesource.com/toolchain/llvm-project d9f89f4d16663d5012e5c09495f3b30ece3d2362)";
char const *LLAMA_BUILD_TARGET = "x86_64-apple-darwin23.5.0";
llamalib/src/main/cpp/llama-cpp/common/build-info.cpp.in 0 → 100644
int LLAMA_BUILD_NUMBER = @BUILD_NUMBER@;
char const *LLAMA_COMMIT = "@BUILD_COMMIT@";
char const *LLAMA_COMPILER = "@BUILD_COMPILER@";
char const *LLAMA_BUILD_TARGET = "@BUILD_TARGET@";
llamalib/src/main/cpp/llama-cpp/common/chat.h 0 → 100644
// Chat support (incl. tool call grammar constraining & output parsing) w/ generic & custom template handlers.
#pragma once
#include "common.h"
#include <string>
#include <vector>
struct common_chat_templates;
struct common_chat_tool_call {
std::string name;
std::string arguments;
std::string id;
};
struct common_chat_msg_content_part {
std::string type;
std::string text;
};
struct common_chat_msg {
std::string role;
std::string content;
std::vector<common_chat_msg_content_part> content_parts = {};
std::vector<common_chat_tool_call> tool_calls = {};
std::string reasoning_content;
std::string tool_name;
std::string tool_call_id;
};
struct common_chat_tool {
std::string name;
std::string description;
std::string parameters;
};
enum common_chat_tool_choice {
COMMON_CHAT_TOOL_CHOICE_AUTO,
COMMON_CHAT_TOOL_CHOICE_REQUIRED,
COMMON_CHAT_TOOL_CHOICE_NONE,
};
enum common_chat_format {
COMMON_CHAT_FORMAT_CONTENT_ONLY,
COMMON_CHAT_FORMAT_GENERIC,
COMMON_CHAT_FORMAT_MISTRAL_NEMO,
COMMON_CHAT_FORMAT_LLAMA_3_X,
COMMON_CHAT_FORMAT_LLAMA_3_X_WITH_BUILTIN_TOOLS,
COMMON_CHAT_FORMAT_DEEPSEEK_R1,
COMMON_CHAT_FORMAT_DEEPSEEK_R1_EXTRACT_REASONING,
COMMON_CHAT_FORMAT_FIREFUNCTION_V2,
COMMON_CHAT_FORMAT_FUNCTIONARY_V3_2,
COMMON_CHAT_FORMAT_FUNCTIONARY_V3_1_LLAMA_3_1,
COMMON_CHAT_FORMAT_HERMES_2_PRO,
COMMON_CHAT_FORMAT_HERMES_2_PRO_EXTRACT_REASONING,
COMMON_CHAT_FORMAT_COMMAND_R7B,
COMMON_CHAT_FORMAT_COMMAND_R7B_EXTRACT_REASONING,
COMMON_CHAT_FORMAT_COUNT, // Not a format, just the # formats
};
struct common_chat_templates_inputs {
std::vector<common_chat_msg> messages;
std::string grammar;
std::string json_schema;
bool add_generation_prompt = true;
bool use_jinja = true;
// Parameters below only supported when use_jinja is true
std::vector<common_chat_tool> tools;
common_chat_tool_choice tool_choice = COMMON_CHAT_TOOL_CHOICE_AUTO;
bool parallel_tool_calls = false;
bool extract_reasoning = true;
};
struct common_chat_params {
common_chat_format format = COMMON_CHAT_FORMAT_CONTENT_ONLY;
std::string prompt;
std::string grammar;
bool grammar_lazy = false;
std::vector<common_grammar_trigger> grammar_triggers;
std::vector<std::string> preserved_tokens;
std::vector<std::string> additional_stops;
};
// Check if the template supplied via "--chat-template" is supported or not. Returns true if it's valid
bool common_chat_verify_template(const std::string & tmpl, bool use_jinja);
void common_chat_templates_free(struct common_chat_templates * tmpls);
struct common_chat_templates_deleter { void operator()(common_chat_templates * tmpls) { common_chat_templates_free(tmpls); } };
typedef std::unique_ptr<struct common_chat_templates, common_chat_templates_deleter> common_chat_templates_ptr;
common_chat_templates_ptr common_chat_templates_init(
const struct llama_model * model,
const std::string & chat_template_override,
const std::string & bos_token_override = "",
const std::string & eos_token_override = "");
bool common_chat_templates_was_explicit(const struct common_chat_templates * tmpls);
const char * common_chat_templates_source(const struct common_chat_templates * tmpls, const char * variant = nullptr);
struct common_chat_params common_chat_templates_apply(
const struct common_chat_templates * tmpls,
const struct common_chat_templates_inputs & inputs);
// Format single message, while taking into account the position of that message in chat history
std::string common_chat_format_single(
const struct common_chat_templates * tmpls,
const std::vector<common_chat_msg> & past_msg,
const common_chat_msg & new_msg,
bool add_ass,
bool use_jinja);
// Returns an example of formatted chat
std::string common_chat_format_example(
const struct common_chat_templates * tmpls,
bool use_jinja);
std::string common_chat_format_name(common_chat_format format);
common_chat_msg common_chat_parse( const std::string & input, common_chat_format format);
common_chat_tool_choice common_chat_tool_choice_parse_oaicompat(const std::string & tool_choice);
// Parses a JSON array of messages in OpenAI's chat completion API format.
// T can be std::string containing JSON or nlohmann::ordered_json
template <class T> std::vector<common_chat_msg> common_chat_msgs_parse_oaicompat(const T & messages);
template <class T> T common_chat_msgs_to_json_oaicompat(const std::vector<common_chat_msg> & msgs, bool concat_typed_text = false);
// Parses a JSON array of tools in OpenAI's chat completion tool call API format.
// T can be std::string containing JSON or nlohmann::ordered_json
template <class T> std::vector<common_chat_tool> common_chat_tools_parse_oaicompat(const T & tools);
template <class T> T common_chat_tools_to_json_oaicompat(const std::vector<common_chat_tool> & tools);
llamalib/src/main/cpp/llama-cpp/common/cmake/build-info-gen-cpp.cmake 0 → 100644
include(${CMAKE_CURRENT_SOURCE_DIR}/cmake/build-info.cmake)
set(TEMPLATE_FILE "${CMAKE_CURRENT_SOURCE_DIR}/common/build-info.cpp.in")
set(OUTPUT_FILE "${CMAKE_CURRENT_SOURCE_DIR}/common/build-info.cpp")
# Only write the build info if it changed
if(EXISTS ${OUTPUT_FILE})
file(READ ${OUTPUT_FILE} CONTENTS)
string(REGEX MATCH "LLAMA_COMMIT = \"([^\"]*)\";" _ ${CONTENTS})
set(OLD_COMMIT ${CMAKE_MATCH_1})
string(REGEX MATCH "LLAMA_COMPILER = \"([^\"]*)\";" _ ${CONTENTS})
set(OLD_COMPILER ${CMAKE_MATCH_1})
string(REGEX MATCH "LLAMA_BUILD_TARGET = \"([^\"]*)\";" _ ${CONTENTS})
set(OLD_TARGET ${CMAKE_MATCH_1})
if (
NOT OLD_COMMIT STREQUAL BUILD_COMMIT OR
NOT OLD_COMPILER STREQUAL BUILD_COMPILER OR
NOT OLD_TARGET STREQUAL BUILD_TARGET
)
configure_file(${TEMPLATE_FILE} ${OUTPUT_FILE})
endif()
else()
configure_file(${TEMPLATE_FILE} ${OUTPUT_FILE})
endif()
llamalib/src/main/cpp/llama-cpp/common/json.hpp 0 → 100644
This diff could not be displayed because it is too large.
llamalib/src/main/cpp/llama-cpp/common/minja/minja.hpp 0 → 100644
This diff could not be displayed because it is too large.
llamalib/src/main/cpp/llama-cpp/common/stb_image.h 0 → 100644
This diff could not be displayed because it is too large.
llamalib/src/main/cpp/llama-cpp/convert_hf_to_gguf.py 0 → 100755
This diff could not be displayed because it is too large.
llamalib/src/main/cpp/llama-cpp/ggml/src/ggml-cann/Doxyfile 0 → 100644
This diff could not be displayed because it is too large.
llamalib/src/main/cpp/llama-cpp/ggml/src/ggml-cann/aclnn_ops.cpp 0 → 100644
This diff could not be displayed because it is too large.
llamalib/src/main/cpp/llama-cpp/ggml/src/ggml-common.h 0 → 100644
This diff could not be displayed because it is too large.
llamalib/src/main/cpp/llama-cpp/ggml/src/ggml-cpu/amx/mmq.cpp 0 → 100644
This diff could not be displayed because it is too large.
llamalib/src/main/cpp/llama-cpp/ggml/src/ggml-cpu/ggml-cpu-aarch64.cpp 0 → 100644
This diff could not be displayed because it is too large.
llamalib/src/main/cpp/llama-cpp/ggml/src/ggml-cpu/ggml-cpu-quants.c 0 → 100644
This diff could not be displayed because it is too large.
llamalib/src/main/cpp/llama-cpp/ggml/src/ggml-cpu/ggml-cpu.c 0 → 100644
This diff could not be displayed because it is too large.
llamalib/src/main/cpp/llama-cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp 0 → 100644
This diff could not be displayed because it is too large.
llamalib/src/main/cpp/llama-cpp/ggml/src/ggml-cpu/ops.cpp 0 → 100644
This diff could not be displayed because it is too large.
llamalib/src/main/cpp/llama-cpp/ggml/src/ggml-cuda/ggml-cuda.cu 0 → 100644
This diff could not be displayed because it is too large.
llamalib/src/main/cpp/llama-cpp/ggml/src/ggml-cuda/mmq.cuh 0 → 100644
This diff could not be displayed because it is too large.
llamalib/src/main/cpp/llama-cpp/ggml/src/ggml-metal/ggml-metal.m 0 → 100644
This diff could not be displayed because it is too large.
llamalib/src/main/cpp/llama-cpp/ggml/src/ggml-metal/ggml-metal.metal 0 → 100644
This diff could not be displayed because it is too large.
llamalib/src/main/cpp/llama-cpp/ggml/src/ggml-opencl/ggml-opencl.cpp 0 → 100644
This diff could not be displayed because it is too large.
llamalib/src/main/cpp/llama-cpp/ggml/src/ggml-quants.c 0 → 100644
This diff could not be displayed because it is too large.
llamalib/src/main/cpp/llama-cpp/ggml/src/ggml-sycl/dpct/helper.hpp 0 → 100644
This diff could not be displayed because it is too large.
llamalib/src/main/cpp/llama-cpp/ggml/src/ggml-sycl/ggml-sycl.cpp 0 → 100644
This diff could not be displayed because it is too large.
llamalib/src/main/cpp/llama-cpp/ggml/src/ggml-sycl/mmq.cpp 0 → 100644
This diff could not be displayed because it is too large.
llamalib/src/main/cpp/llama-cpp/ggml/src/ggml-vulkan/ggml-vulkan.cpp 0 → 100644
This diff could not be displayed because it is too large.
llamalib/src/main/cpp/llama-cpp/ggml/src/ggml.c 0 → 100644
This diff could not be displayed because it is too large.
llamalib/src/main/cpp/llama-cpp/models/ggml-vocab-command-r.gguf 0 → 100644
The file could not be displayed because it is too large.
llamalib/src/main/cpp/llama-cpp/poetry.lock 0 → 100644
This diff could not be displayed because it is too large.
llamalib/src/main/cpp/llama-cpp/src/llama-model.cpp 0 → 100644
This diff could not be displayed because it is too large.
llamalib/src/main/cpp/llama-cpp/src/llama-vocab.cpp 0 → 100644
This diff could not be displayed because it is too large.
llamalib/src/main/cpp/llama-cpp/src/unicode-data.cpp 0 → 100644
This diff could not be displayed because it is too large.
llamalib/src/main/cpp/llama-cpp/tests/test-backend-ops.cpp 0 → 100644
This diff could not be displayed because it is too large.
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or sign in to comment