vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-05-18 23:49:46 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.github/workflows/build-android.yml
#	.github/workflows/build.yml
#	.github/workflows/release.yml
#	CMakeLists.txt
#	CODEOWNERS
#	common/CMakeLists.txt
#	common/common.h
#	docs/ops.md
#	docs/ops/Metal.csv
#	examples/batched/CMakeLists.txt
#	examples/convert-llama2c-to-ggml/CMakeLists.txt
#	examples/debug/CMakeLists.txt
#	examples/diffusion/CMakeLists.txt
#	examples/embedding/CMakeLists.txt
#	examples/eval-callback/CMakeLists.txt
#	examples/gen-docs/CMakeLists.txt
#	examples/idle/CMakeLists.txt
#	examples/lookahead/CMakeLists.txt
#	examples/lookup/CMakeLists.txt
#	examples/parallel/CMakeLists.txt
#	examples/passkey/CMakeLists.txt
#	examples/retrieval/CMakeLists.txt
#	examples/save-load-state/CMakeLists.txt
#	examples/speculative-simple/CMakeLists.txt
#	examples/speculative/CMakeLists.txt
#	examples/sycl/CMakeLists.txt
#	examples/training/CMakeLists.txt
#	ggml/src/ggml-hexagon/htp/hmx-matmul-ops.c
#	ggml/src/ggml-hexagon/htp/htp-ops.h
#	ggml/src/ggml-hexagon/htp/main.c
#	ggml/src/ggml-opencl/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-opencl/kernels/cvt.cl
#	pocs/vdot/CMakeLists.txt
#	src/CMakeLists.txt
#	tests/CMakeLists.txt
#	tests/test-quantize-stats.cpp
#	tools/batched-bench/CMakeLists.txt
#	tools/cli/CMakeLists.txt
#	tools/cli/cli.cpp
#	tools/completion/CMakeLists.txt
#	tools/cvector-generator/CMakeLists.txt
#	tools/cvector-generator/cvector-generator.cpp
#	tools/export-lora/CMakeLists.txt
#	tools/gguf-split/CMakeLists.txt
#	tools/gguf-split/gguf-split.cpp
#	tools/imatrix/CMakeLists.txt
#	tools/llama-bench/CMakeLists.txt
#	tools/llama-bench/llama-bench.cpp
#	tools/mtmd/CMakeLists.txt
#	tools/perplexity/CMakeLists.txt
#	tools/quantize/CMakeLists.txt
#	tools/quantize/quantize.cpp
#	tools/results/CMakeLists.txt
#	tools/server/CMakeLists.txt
#	tools/tokenize/CMakeLists.txt
#	tools/tts/CMakeLists.txt
This commit is contained in:
Concedo 2026-04-17 22:37:37 +08:00
commit 79882d669a
146 changed files with 1507 additions and 2103 deletions
Download patch file Download diff file Expand all files Collapse all files

6
common/arg.cpp
View file

@ -1,5 +1,6 @@
#include "arg.h"
#include "build-info.h"
#include "chat.h"
#include "common.h"
#include "download.h"
@ -9,7 +10,6 @@
#include "sampling.h"
#include "speculative.h"
#include "chat.h"
#include "build-info.h"
#include "preset.h"
// fix problem with std::min and std::max
@ -1047,8 +1047,8 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
{"--version"},
"show version and build info",
[](common_params &) {
fprintf(stderr, "version: %d (%s)\n", LLAMA_BUILD_NUMBER, LLAMA_COMMIT);
fprintf(stderr, "built with %s for %s\n", LLAMA_COMPILER, LLAMA_BUILD_TARGET);
fprintf(stderr, "version: %d (%s)\n", llama_build_number(), llama_commit());
fprintf(stderr, "built with %s for %s\n", llama_compiler(), llama_build_target());
exit(0);
}
));

37
common/build-info.cpp.in
View file

@ -1,4 +1,35 @@
#include "build-info.h"
#include <cstdio>
#include <string>
int LLAMA_BUILD_NUMBER = @LLAMA_BUILD_NUMBER@;
char const *LLAMA_COMMIT = "@LLAMA_BUILD_COMMIT@";
char const *LLAMA_COMPILER = "@BUILD_COMPILER@";
char const *LLAMA_BUILD_TARGET = "@BUILD_TARGET@";
char const * LLAMA_COMMIT = "@LLAMA_BUILD_COMMIT@";
char const * LLAMA_COMPILER = "@BUILD_COMPILER@";
char const * LLAMA_BUILD_TARGET = "@BUILD_TARGET@";
int llama_build_number(void) {
return LLAMA_BUILD_NUMBER;
}
const char * llama_commit(void) {
return LLAMA_COMMIT;
}
const char * llama_compiler(void) {
return LLAMA_COMPILER;
}
const char * llama_build_target(void) {
return LLAMA_BUILD_TARGET;
}
const char * llama_build_info(void) {
static std::string s = "b" + std::to_string(LLAMA_BUILD_NUMBER) + "-" + LLAMA_COMMIT;
return s.c_str();
}
void llama_print_build_info(void) {
fprintf(stderr, "%s: build = %d (%s)\n", __func__, llama_build_number(), llama_commit());
fprintf(stderr, "%s: built with %s for %s\n", __func__, llama_compiler(), llama_build_target());
}

40
common/build-info.h Normal file
View file

@ -0,0 +1,40 @@
#ifndef BUILD_INFO_H
#define BUILD_INFO_H
#define LLAMA_BUILD_NUMBER 999
#define LLAMA_COMMIT "KOBOLDCPP"
#define LLAMA_COMPILER "KCPP"
#define LLAMA_TARGET "KCPP"
#define LLAMA_BUILD_COMMIT "KOBOLDCPP"
#define LLAMA_BUILD_COMPILER "KCPP"
#define LLAMA_BUILD_TARGET "KCPP"
#include <string>
static inline int llama_build_number(void) {
return LLAMA_BUILD_NUMBER;
}
static inline const char * llama_commit(void) {
return LLAMA_COMMIT;
}
static inline const char * llama_compiler(void) {
return LLAMA_COMPILER;
}
static inline const char * llama_build_target(void) {
return LLAMA_BUILD_TARGET;
}
static inline const char * llama_build_info(void) {
static std::string s = "b" + std::to_string(LLAMA_BUILD_NUMBER) + "-" + LLAMA_COMMIT;
return s.c_str();
}
static inline void llama_print_build_info(void) {
fprintf(stderr, "%s: build = %d (%s)\n", __func__, llama_build_number(), llama_commit());
fprintf(stderr, "%s: built with %s for %s\n", __func__, llama_compiler(), llama_build_target());
}
#endif // BUILD_INFO_H

4
common/common.cpp
View file

@ -1,9 +1,9 @@
#include "ggml.h"
#include "gguf.h"
#include "build-info.h"
#include "common.h"
#include "log.h"
#include "build-info.h"
#include "log.cpp"
// Change JSON_ASSERT from assert() to GGML_ASSERT:
#define JSON_ASSERT GGML_ASSERT
@ -379,7 +379,7 @@ void common_init() {
const char * build_type = " (debug)";
#endif
LOG_DBG("build: %d (%s) with %s for %s%s\n", LLAMA_BUILD_NUMBER, LLAMA_COMMIT, LLAMA_COMPILER, LLAMA_BUILD_TARGET, build_type);
LOG_DBG("build: %d (%s) with %s for %s%s\n", llama_build_number(), llama_commit(), llama_compiler(), llama_build_target(), build_type);
}
std::string common_params_get_system_info(const common_params & params) {

14
common/common.h
View file

@ -2,10 +2,11 @@
#pragma once
#include "build-info.h"
#include "llama-cpp.h"
#include "ggml-opt.h"
#include "ggml.h"
#include "llama-cpp.h"
#include "build-info.h"
#include <set>
#include <sstream>
@ -28,11 +29,6 @@
#define die(msg) do { fputs("error: " msg "\n", stderr); exit(1); } while (0)
#define die_fmt(fmt, ...) do { fprintf(stderr, "error: " fmt "\n", __VA_ARGS__); exit(1); } while (0)
#define print_build_info() do { \
fprintf(stderr, "%s: build = %d (%s)\n", __func__, LLAMA_BUILD_NUMBER, LLAMA_COMMIT); \
fprintf(stderr, "%s: built with %s for %s\n", __func__, LLAMA_COMPILER, LLAMA_BUILD_TARGET); \
} while(0)
struct common_time_meas {
common_time_meas(int64_t & t_acc, bool disable = false);
~common_time_meas();
@ -54,10 +50,6 @@ struct common_adapter_lora_info {
using llama_tokens = std::vector<llama_token>;
// build info
const static std::string build_info("b" + std::to_string(LLAMA_BUILD_NUMBER) + "-" + LLAMA_COMMIT);
struct common_control_vector_load_info;
//

5
common/download.cpp
View file

@ -1,5 +1,6 @@
#include "arg.h"
#include "build-info.h"
#include "common.h"
#include "log.h"
#include "download.h"
@ -306,7 +307,7 @@ static int common_download_file_single_online(const std::string & url,
headers.emplace(h.first, h.second);
}
if (headers.find("User-Agent") == headers.end()) {
headers.emplace("User-Agent", "llama-cpp/" + build_info);
headers.emplace("User-Agent", "llama-cpp/" + std::string(llama_build_info()));
}
if (!opts.bearer_token.empty()) {
headers.emplace("Authorization", "Bearer " + opts.bearer_token);
@ -444,7 +445,7 @@ std::pair<long, std::vector<char>> common_remote_get_content(const std::string
headers.emplace(h.first, h.second);
}
if (headers.find("User-Agent") == headers.end()) {
headers.emplace("User-Agent", "llama-cpp/" + build_info);
headers.emplace("User-Agent", "llama-cpp/" + std::string(llama_build_info()));
}
if (params.timeout > 0) {

3
common/hf-cache.cpp
View file

@ -1,5 +1,6 @@
#include "hf-cache.h"
#include "build-info.h"
#include "common.h"
#include "log.h"
#include "http.h"
@ -200,7 +201,7 @@ static nl::json api_get(const std::string & url,
auto [cli, parts] = common_http_client(url);
httplib::Headers headers = {
{"User-Agent", "llama-cpp/" + build_info},
{"User-Agent", "llama-cpp/" + std::string(llama_build_info())},
{"Accept", "application/json"}
};

4
common/log.cpp
View file

@ -23,6 +23,10 @@
int common_log_verbosity_thold = LOG_DEFAULT_LLAMA;
int common_log_get_verbosity_thold(void) {
return common_log_verbosity_thold;
}
void common_log_set_verbosity_thold(int verbosity) {
common_log_verbosity_thold = verbosity;
}

4
common/log.h
View file

@ -38,7 +38,7 @@ enum log_colors {
// needed by the LOG_TMPL macro to avoid computing log arguments if the verbosity lower
// set via common_log_set_verbosity()
extern int common_log_verbosity_thold;
int common_log_get_verbosity_thold(void);
void common_log_set_verbosity_thold(int verbosity); // not thread-safe
@ -98,7 +98,7 @@ void common_log_flush (struct common_log * log); // f
#define LOG_TMPL(level, verbosity, ...) \
do { \
if ((verbosity) <= common_log_verbosity_thold) { \
if ((verbosity) <= common_log_get_verbosity_thold()) { \
common_log_add(common_log_main(), (level), __VA_ARGS__); \
} \
} while (0)