|
TinyLlama.cpp 1.0
A lightweight C++ implementation of the TinyLlama language model
|
#include "model.h"#include <algorithm>#include <cmath>#include <cstring>#include <fstream>#include <iomanip>#include <limits>#include <memory>#include <sstream>#include <stdexcept>#include <cassert>#include <cstdint>#include <iostream>#include <numeric>#include <variant>#include "cpu_attention.h"#include "cpu_batch_processor.h"#include "gguf_parser.h"#include "gpu_initialization.h"#include "kv_cache.h"#include "logger.h"#include "model_config.h"#include "model_constants.h"#include "model_macros.h"#include "model_utils.h"#include "quantization.h"#include "safetensors_loader.h"#include "utils.h"#include "weight_management.h"