mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-08-04 09:00:48 -05:00
51 lines
1.3 KiB
C++
51 lines
1.3 KiB
C++
#pragma once
|
|
|
|
#define LLAMA_API_INTERNAL
|
|
#include "llama.h"
|
|
|
|
#include <array>
|
|
#include <set>
|
|
#include <map>
|
|
#include <cstdint>
|
|
#include <random>
|
|
|
|
#ifdef __has_include
|
|
#if __has_include(<unistd.h>)
|
|
#include <unistd.h>
|
|
#if defined(_POSIX_MAPPED_FILES)
|
|
#include <sys/mman.h>
|
|
#include <fcntl.h>
|
|
#endif
|
|
#if defined(_POSIX_MEMLOCK_RANGE)
|
|
#include <sys/resource.h>
|
|
#endif
|
|
#endif
|
|
#endif
|
|
|
|
// bump if necessary
|
|
#define LLAMA_MAX_NODES 8192
|
|
#define LLAMA_MAX_LAYERS 256
|
|
#define LLAMA_MAX_EXPERTS 160 // DeepSeekV2
|
|
|
|
#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_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__)
|