ollama/llama/llama-impl.h

/**
 * llama.cpp - commit 46e3556e01b824e52395fb050b29804b6cff2a7c - do not edit this file
 *
 * 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.
 */

#pragma once

#include "ggml.h" // for ggml_log_level

#include <string>
#include <vector>

#ifdef __GNUC__
#ifdef __MINGW32__
#define LLAMA_ATTRIBUTE_FORMAT(...) __attribute__((format(gnu_printf, __VA_ARGS__)))
#else
#define LLAMA_ATTRIBUTE_FORMAT(...) __attribute__((format(printf, __VA_ARGS__)))
#endif
#else
#define LLAMA_ATTRIBUTE_FORMAT(...)
#endif

//
// logging
//

LLAMA_ATTRIBUTE_FORMAT(2, 3)
void llama_log_internal        (ggml_log_level level, const char * format, ...);
void llama_log_callback_default(ggml_log_level level, const char * text, void * user_data);

#define LLAMA_LOG(...)       llama_log_internal(GGML_LOG_LEVEL_NONE , __VA_ARGS__)
#define LLAMA_LOG_INFO(...)  llama_log_internal(GGML_LOG_LEVEL_INFO , __VA_ARGS__)
#define LLAMA_LOG_WARN(...)  llama_log_internal(GGML_LOG_LEVEL_WARN , __VA_ARGS__)
#define LLAMA_LOG_ERROR(...) llama_log_internal(GGML_LOG_LEVEL_ERROR, __VA_ARGS__)
#define LLAMA_LOG_DEBUG(...) llama_log_internal(GGML_LOG_LEVEL_DEBUG, __VA_ARGS__)
#define LLAMA_LOG_CONT(...)  llama_log_internal(GGML_LOG_LEVEL_CONT , __VA_ARGS__)

//
// helpers
//

template <typename T>
struct no_init {
    T value;
    no_init() { /* do nothing */ }
};

struct time_meas {
    time_meas(int64_t & t_acc, bool disable = false);
    ~time_meas();

    const int64_t t_start_us;

    int64_t & t_acc;
};

void replace_all(std::string & s, const std::string & search, const std::string & replace);

// TODO: rename to llama_format ?
LLAMA_ATTRIBUTE_FORMAT(1, 2)
std::string format(const char * fmt, ...);

std::string llama_format_tensor_shape(const std::vector<int64_t> & ne);
std::string llama_format_tensor_shape(const struct ggml_tensor * t);

std::string gguf_kv_to_str(const struct gguf_context * ctx_gguf, int i);