การเร่งความเร็ว NPU ด้วย LiteRT

my_app/
    ...
    ai_packs/
        my_model/...
        my_model_mtk/...

// my_app/ai_packs/my_model/build.gradle.kts

plugins { id("com.android.ai-pack") }

aiPack {
  packName = "my_model"  // ai pack dir name
  dynamicDelivery { deliveryType = "on-demand" }
}

// Add another build.gradle.kts for my_model_mtk/ as well

// my_app/setting.gradle.kts

...
// AI Packs
include(":ai_packs:my_model")
include(":ai_packs:my_model_mtk")

// my_app/build.gradle.kts

android {
 ...

 defaultConfig {
    ...
    // API level 31+ is required for NPU support.
    minSdk = 31
  }

  // AI Packs
  assetPacks.add(":ai_packs:my_model")
  assetPacks.add(":ai_packs:my_model_mtk")
}

val env = Environment.create(BuiltinNpuAcceleratorProvider(context))

val cpuGpuModelProvider =
      ModelProvider.staticModel(
        ModelProvider.Type.ASSET,
        "model/my_model_cpu_gpu.tflite",
        if (accelerator != Accelerator.NPU) accelerator else Accelerator.CPU,
      )

val qualcommNpuModelProvider =
  AiPackModelProvider(context, "my_model", "model/my_model.tflite")
  {
    buildSet {
      if (
        accelerator == Accelerator.NPU && NpuCompatibilityChecker.Qualcomm.isDeviceSupported()
      )
        add(Accelerator.NPU)
    }
  }

val mtkNpuModelProvider =
  AiPackModelProvider(context, "my_model_mtk", "model/my_model.tflite")
  {
    buildSet {
      if (
        accelerator == Accelerator.NPU && NpuCompatibilityChecker.Mediatek.isDeviceSupported()
      )
        add(Accelerator.NPU)
    }
  }

val googleTensorTpuModelProvider =
  AiPackModelProvider(context, "my_model", "model/my_model.tflite")
  {
    buildSet {
      if (accelerator == Accelerator.NPU &&
          NpuCompatibilityChecker.GoogleTensor.isDeviceSupported()
      )
        add(Accelerator.NPU)
    }
  }

val aiPackModelProvider =
        ModelSelector(cpuGpuModelProvider, mtkNpuModelProvider, qualcommNpuModelProvider, googleTensorTpuModelProvider)
          .selectModel(env)

val compiledModel = CompiledModel.create(
    model.getPath(),
    CompiledModel.Options(model.getCompatibleAccelerators()),
    env,
)

my_app/
    ...
    litert_npu_runtime_libraries/
        google_tensor_runtime/...
        mediatek_runtime/...
        qualcomm_runtime_v69/...
        qualcomm_runtime_v73/...
        qualcomm_runtime_v75/...
        qualcomm_runtime_v79/...
        qualcomm_runtime_v81/...
        fetch_qualcomm_library.sh

$ ./litert_npu_runtime_libraries/fetch_qualcomm_library.sh

// my_app/setting.gradle.kts

...
// NPU runtime libraries
include(":litert_npu_runtime_libraries:runtime_strings")
include(":litert_npu_runtime_libraries:google_tensor_runtime")
include(":litert_npu_runtime_libraries:mediatek_runtime")
include(":litert_npu_runtime_libraries:qualcomm_runtime_v69")
include(":litert_npu_runtime_libraries:qualcomm_runtime_v73")
include(":litert_npu_runtime_libraries:qualcomm_runtime_v75")
include(":litert_npu_runtime_libraries:qualcomm_runtime_v79")
include(":litert_npu_runtime_libraries:qualcomm_runtime_v81")

// my_app/build.gradle.kts

android {
 ...
 defaultConfig {
    ...
    // API level 31+ is required for NPU support.
    minSdk = 31

    // NPU only supports arm64-v8a
    ndk { abiFilters.add("arm64-v8a") }
    // Needed for Qualcomm NPU runtime libraries
    packaging { jniLibs { useLegacyPackaging = true } }
  }

  // Device targeting
  bundle {
      deviceTargetingConfig = file("device_targeting_configuration.xml")
      deviceGroup {
        enableSplit = true // split bundle by #group
        defaultGroup = "other" // group used for standalone APKs
      }
  }

  // NPU runtime libraries
  dynamicFeatures.add(":litert_npu_runtime_libraries:google_tensor_runtime")
  dynamicFeatures.add(":litert_npu_runtime_libraries:mediatek_runtime")
  dynamicFeatures.add(":litert_npu_runtime_libraries:qualcomm_runtime_v69")
  dynamicFeatures.add(":litert_npu_runtime_libraries:qualcomm_runtime_v73")
  dynamicFeatures.add(":litert_npu_runtime_libraries:qualcomm_runtime_v75")
  dynamicFeatures.add(":litert_npu_runtime_libraries:qualcomm_runtime_v79")
  dynamicFeatures.add(":litert_npu_runtime_libraries:qualcomm_runtime_v81")
}

dependencies {
  // Dependencies for strings used in the runtime library modules.
  implementation(project(":litert_npu_runtime_libraries:runtime_strings"))
  ...
}

dependencies {
  ...
  implementation("com.google.ai.edge.litert:litert:+")
}

// 1. Load model and initialize runtime.
// If NPU is unavailable, inference will fallback to GPU.
val model =
    CompiledModel.create(
        context.assets,
        "model/mymodel.tflite",
        CompiledModel.Options(Accelerator.NPU, Accelerator.GPU)
    )

// 2. Pre-allocate input/output buffers
val inputBuffers = model.createInputBuffers()
val outputBuffers = model.createOutputBuffers()

// 3. Fill the first input
inputBuffers[0].writeFloat(...)

// 4. Invoke
model.run(inputBuffers, outputBuffers)

// 5. Read the output
val outputFloatArray = outputBuffers[0].readFloat()

// Provide a dispatch library directory (following is a hypothetical path) for the NPU
std::vector<Environment::Option> environment_options = {
    {
      Environment::OptionTag::DispatchLibraryDir,
      "/usr/lib64/npu_dispatch/"
    }
};

LITERT_ASSIGN_OR_RETURN(auto env, Environment::Create(absl::MakeConstSpan(environment_options)));

// 1. Load the model that has NPU-compatible ops
LITERT_ASSIGN_OR_RETURN(auto model, Model::Load("mymodel_npu.tflite"));

// 2. Create a compiled model with NPU acceleration
//    See following section on how to set up NPU environment
LITERT_ASSIGN_OR_RETURN(auto compiled_model,
  CompiledModel::Create(env, model, kLiteRtHwAcceleratorNpu));

// 3. Allocate I/O buffers
LITERT_ASSIGN_OR_RETURN(auto input_buffers, compiled_model.CreateInputBuffers());
LITERT_ASSIGN_OR_RETURN(auto output_buffers, compiled_model.CreateOutputBuffers());

// 4. Fill model inputs (CPU array -> NPU buffers)
float input_data[] = { /* your input data */ };
input_buffers[0].Write<float>(absl::MakeConstSpan(input_data, /*size*/));

// 5. Run inference
compiled_model.Run(input_buffers, output_buffers);

// 6. Access model output
std::vector<float> data(output_data_size);
output_buffers[0].Read<float>(absl::MakeSpan(data));

// Suppose you have AHardwareBuffer* ahw_buffer

LITERT_ASSIGN_OR_RETURN(auto tensor_type, model.GetInputTensorType("input_tensor"));

LITERT_ASSIGN_OR_RETURN(auto npu_input_buffer, TensorBuffer::CreateFromAhwb(
    env,
    tensor_type,
    ahw_buffer,
    /* offset = */ 0
));

std::vector<TensorBuffer> input_buffers{npu_input_buffer};

LITERT_ASSIGN_OR_RETURN(auto output_buffers, compiled_model.CreateOutputBuffers());

// Execute the model
compiled_model.Run(input_buffers, output_buffers);

// Retrieve the output (possibly also an AHWB or other specialized buffer)
auto ahwb_output = output_buffers[0].GetAhwb();

// compiled_model1 outputs into an AHWB
compiled_model1.Run(input_buffers, intermediate_buffers);

// compiled_model2 consumes that same AHWB
compiled_model2.Run(intermediate_buffers, final_outputs);

   const std::array environment_options = {
        litert::Environment::Option{
            /*.tag=*/litert::Environment::OptionTag::CompilerPluginLibraryDir,
            /*.value=*/kCompilerPluginLibSearchPath,
        },
        litert::Environment::Option{
            litert::Environment::OptionTag::DispatchLibraryDir,
            kDispatchLibraryDir,
        },
        // 'kCompilerCacheDir' will be used to store NPU-compiled model
        // artifacts.
        litert::Environment::Option{
            litert::Environment::OptionTag::CompilerCacheDir,
            kCompilerCacheDir,
        },
    };

    // Create an environment.
    LITERT_ASSERT_OK_AND_ASSIGN(
        auto environment, litert::Environment::Create(environment_options));

    // Load a model.
    auto model_path = litert::testing::GetTestFilePath(kModelFileName);
    LITERT_ASSERT_OK_AND_ASSIGN(auto model,
                                litert::Model::CreateFromFile(model_path));

    // Create a compiled model, which only triggers NPU compilation if
    // required.
    LITERT_ASSERT_OK_AND_ASSIGN(
        auto compiled_model, litert::CompiledModel::Create(
                                 environment, model, kLiteRtHwAcceleratorNpu));