GemmaModel.ixx File Reference

Gemma 4 inference model. More...

#include <memory>
#include <vector>
#include <span>
#include <unordered_set>
#include <string>
#include <sstream>
#include <cstdint>
#include <stdexcept>
#include <filesystem>
#include <format>
#include <random>
#include <optional>
#include <chrono>
#include <algorithm>
#include <numeric>
#include <functional>
#include <stop_token>
#include <cstring>
#include <type_traits>
#include <cmath>
#include <limits>
import Logging.Logger;
import Dnn.TensorDataType;
import Dnn.ITensor;
import Dnn.Quantization.KvCache.QuantPolicy;
import Compute.DeviceTypeTraits;
import Dnn.Quantization.KvCache.Policy;
import Dnn.GenerateParams;
import Dnn.TensorDataTypeTraits;
import Dnn.Quantization.Weight.Policies;
import Dnn.Component;
import Compute.DeviceId;
import Dnn.LanguageNetwork;
import Dnn.LanguageModelConfig;
import Dnn.Models.GemmaModelConfig;
import Dnn.Models.QuantizationDispatch;
import Compute.DeviceTypeTraits.Cpu;
import Dnn.Components.GemmaTransformer;
import Dnn.LanguageModel;
import Dnn.Components.GemmaConfig;
import Dnn.GenerateStatus;
import Compute.Device;
import Compute.DeviceType;
import Serialization.Mode;
import Compute.CpuMemoryResource;
import Compute.ExecutionContextFactory;
import Dnn.TensorTypes;
import Dnn.Tensor;
import Dnn.RuntimeMode;
import Serialization.PretrainedReader;
import Serialization.SafeTensors;

Classes
class	Mila::Dnn::GemmaModel< TDeviceType, TPrecision >
	Gemma 4 compatible inference model. More...

Namespaces
namespace	Mila
	Mila main API namespace.

Detailed Description

Gemma 4 inference model.

Inference-only wrapper around a loaded GemmaTransformer network.