CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-21 12:16:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

common : more accurate sampling timing (#17382)

Browse Source 
* common : more accurate sampling timing

* eval-callback : minor fixes

* cont : add time_meas impl

* cont : fix log msg [no ci]

* cont : fix multiple definitions of time_meas

* llama-cli : exclude chat template init from time measurement

* cont : print percentage of unaccounted time

* cont : do not reset timings
This commit is contained in:
Georgi Gerganov
2025-11-20 13:40:10 +02:00
committed by GitHub
parent 5088b435d4
commit 196f5083ef
7 changed files with 102 additions and 33 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
common/common.h
View File

@@ -2,17 +2,15 @@
#pragma once
#include "ggml-opt.h"
#include "llama-cpp.h"
#include <set>
#include <sstream>
#include <string>
#include <string_view>
#include <vector>
#include <map>
#include <sstream>
#include <cmath>
#include "ggml-opt.h"
#include "llama-cpp.h"
#ifdef _WIN32
#define DIRECTORY_SEPARATOR '\\'
@@ -30,6 +28,15 @@
#define DEFAULT_MODEL_PATH "models/7B/ggml-model-f16.gguf"
struct common_time_meas {
common_time_meas(int64_t & t_acc, bool disable = false);
~common_time_meas();
const int64_t t_start_us;
int64_t & t_acc;
};
struct common_adapter_lora_info {
std::string path;
float scale;