‫LiteRT CompiledModel C++ API

cc_binary(
    name = "your_application",
    srcs = [
        "main.cc",
    ],
    data = [
        ...
        # litert c api shared library
        "//litert/c:litert_runtime_c_api_shared_lib",
        # GPU accelerator shared library
        "@litert_gpu//:jni/arm64-v8a/libLiteRtGpuAccelerator.so",
        # NPU accelerator shared library
        "//litert/vendors/qualcomm/dispatch:dispatch_api_so",
    ],
    linkopts = select({
        "@org_tensorflow//tensorflow:android": ["-landroid"],
        "//conditions:default": [],
    }) + gles_linkopts(), # gles link options
    deps = [
        ...
        "//litert/cc:litert_tensor_buffer", # litert cc library
        ...
    ] + gles_deps(), # gles dependencies
)

LITERT_ASSIGN_OR_RETURN(auto model, Model::CreateFromFile("mymodel.tflite"));

LITERT_ASSIGN_OR_RETURN(auto env, Environment::Create({}));

LITERT_ASSIGN_OR_RETURN(auto compiled_model,
  CompiledModel::Create(env, model, kLiteRtHwAcceleratorCpu));

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

input_buffers[0].Write<float>(absl::MakeConstSpan(input_data, input_size));

compiled_model.Run(input_buffers, output_buffers);

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

LITERT_ASSIGN_OR_RETURN(auto reqs, compiled_model.GetInputBufferRequirements(signature_index, input_index));

LITERT_ASSIGN_OR_RETURN(auto tensor_buffer_cpu,
TensorBuffer::CreateManaged(env, /*buffer_type=*/kLiteRtTensorBufferTypeHostMemory,
  ranked_tensor_type, buffer_size));

LITERT_ASSIGN_OR_RETURN(auto tensor_buffer_gl, TensorBuffer::CreateManaged(env,
  /*buffer_type=*/kLiteRtTensorBufferTypeGlBuffer, ranked_tensor_type, buffer_size));

LITERT_ASSIGN_OR_RETURN(auto tensor_buffer_ahwb, TensorBuffer::CreateManaged(env,
  /*buffer_type=*/kLiteRtTensorBufferTypeAhwb, ranked_tensor_type, buffer_size));

// Create a TensorBuffer from host memory
LITERT_ASSIGN_OR_RETURN(auto tensor_buffer_from_host,
  TensorBuffer::CreateFromHostMemory(env, ranked_tensor_type,
  ptr_to_host_memory, buffer_size));

// Create a TensorBuffer from GlBuffer
LITERT_ASSIGN_OR_RETURN(auto tensor_buffer_from_gl,
  TensorBuffer::CreateFromGlBuffer(env, ranked_tensor_type, gl_target, gl_id,
  size_bytes, offset));

// Create a TensorBuffer from AHardware Buffer
LITERT_ASSIGN_OR_RETURN(auto tensor_buffer_from_ahwb,
  TensorBuffer::CreateFromAhwb(env, ranked_tensor_type, ahardware_buffer, offset));

// Example of reading to input buffer:
std::vector<float> input_tensor_data = {1,2};
LITERT_ASSIGN_OR_RETURN(auto write_success,
  input_tensor_buffer.Write<float>(absl::MakeConstSpan(input_tensor_data)));
if(write_success){
  /* Continue after successful write... */
}

// Example of writing to output buffer:
std::vector<float> data(total_elements);
LITERT_ASSIGN_OR_RETURN(auto read_success,
  output_tensor_buffer.Read<float>(absl::MakeSpan(data)));
if(read_success){
  /* Continue after successful read */
}

LITERT_ASSIGN_OR_RETURN(auto tensor_buffer_ahwb,
  TensorBuffer::CreateManaged(env, kLiteRtTensorBufferTypeAhwb,
  ranked_tensor_type, buffer_size));
// Buffer interop: Get OpenGL buffer from AHWB,
// internally creating an OpenGL buffer backed by AHWB memory.
LITERT_ASSIGN_OR_RETURN(auto gl_buffer, tensor_buffer_ahwb.GetGlBuffer());

LITERT_ASSIGN_OR_RETURN(auto cl_buffer, tensor_buffer_ahwb.GetOpenClMemory());

LITERT_ASSIGN_OR_RETURN(auto tensor_buffer_from_gl,
  TensorBuffer::CreateFromGlBuffer(env, ranked_tensor_type, gl_target, gl_id,
  size_bytes, offset));

// Creates an OpenCL buffer from the OpenGL buffer, zero-copy.
LITERT_ASSIGN_OR_RETURN(auto cl_buffer, tensor_buffer_from_gl.GetOpenClMemory());

// Load model and initialize runtime
LITERT_ASSIGN_OR_RETURN(auto model, Model::CreateFromFile("mymodel.tflite"));
LITERT_ASSIGN_OR_RETURN(auto env, Environment::Create({}));
LITERT_ASSIGN_OR_RETURN(auto compiled_model, CompiledModel::Create(env, model,
  kLiteRtHwAcceleratorCpu));

// Preallocate input/output buffers
LITERT_ASSIGN_OR_RETURN(auto input_buffers, compiled_model.CreateInputBuffers());
LITERT_ASSIGN_OR_RETURN(auto output_buffers, compiled_model.CreateOutputBuffers());

// Fill the first input
float input_values[] = { /* your data */ };
input_buffers[0].Write<float>(absl::MakeConstSpan(input_values, /*size*/));

// Invoke
compiled_model.Run(input_buffers, output_buffers);

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

// Define an LiteRT environment to use existing EGL display and context.
const std::vector<Environment::Option> environment_options = {
   {OptionTag::EglDisplay, user_egl_display},
   {OptionTag::EglContext, user_egl_context}};
LITERT_ASSIGN_OR_RETURN(auto env,
   Environment::Create(absl::MakeConstSpan(environment_options)));

// Load model1 and initialize runtime.
LITERT_ASSIGN_OR_RETURN(auto model1, Model::CreateFromFile("model1.tflite"));
LITERT_ASSIGN_OR_RETURN(auto compiled_model1, CompiledModel::Create(env, model1, kLiteRtHwAcceleratorGpu));

// Prepare I/O buffers. opengl_buffer is given outside from the producer.
LITERT_ASSIGN_OR_RETURN(auto tensor_type, model.GetInputTensorType("input_name0"));
// Create an input TensorBuffer based on tensor_type that wraps the given OpenGL Buffer.
LITERT_ASSIGN_OR_RETURN(auto tensor_buffer_from_opengl,
    litert::TensorBuffer::CreateFromGlBuffer(env, tensor_type, opengl_buffer));

// Create an input event and attach it to the input buffer. Internally, it creates
// and inserts a fence sync object into the current EGL command queue.
LITERT_ASSIGN_OR_RETURN(auto input_event, Event::CreateManaged(env, LiteRtEventTypeEglSyncFence));
tensor_buffer_from_opengl.SetEvent(std::move(input_event));

std::vector<TensorBuffer> input_buffers;
input_buffers.push_back(std::move(tensor_buffer_from_opengl));

// Create an output TensorBuffer of the model1. It's also used as an input of the model2.
LITERT_ASSIGN_OR_RETURN(auto intermedidate_buffers,  compiled_model1.CreateOutputBuffers());

// Load model2 and initialize runtime.
LITERT_ASSIGN_OR_RETURN(auto model2, Model::CreateFromFile("model2.tflite"));
LITERT_ASSIGN_OR_RETURN(auto compiled_model2, CompiledModel::Create(env, model2, kLiteRtHwAcceleratorGpu));
LITERT_ASSIGN_OR_RETURN(auto output_buffers, compiled_model2.CreateOutputBuffers());

compiled_model1.RunAsync(input_buffers, intermedidate_buffers);
compiled_model2.RunAsync(intermedidate_buffers, output_buffers);