vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-07-21 06:43:33 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge commit '6effcecd0b' into concedo_experimental

Browse source 
# Conflicts:
#	.github/workflows/build-msys.yml
#	.pi/gg/SYSTEM.md
#	common/CMakeLists.txt
#	examples/speculative-simple/speculative-simple.cpp
#	ggml/src/ggml-cpu/kleidiai/kleidiai.cpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-sycl/mmvq.cpp
#	scripts/ui-assets.cmake
#	src/llama-model.cpp
#	tools/cli/cli.cpp
#	tools/imatrix/imatrix.cpp
#	tools/quantize/quantize.cpp
#	tools/server/README.md
#	tools/ui/tests/stories/a11y/ChatScreenForm.a11y.stories.svelte
This commit is contained in:
Concedo 2026-06-07 17:10:58 +08:00
commit 202aaef40b
152 changed files with 1188 additions and 878 deletions
Download patch file Download diff file Expand all files Collapse all files

225
tools/quantize/quantize.cpp
View file

@ -1,6 +1,7 @@
#include "llama.h"
#include "build-info.h"
#include "common/common.h"
#include "common/imatrix-loader.h"
#include "gguf.h"
@ -13,7 +14,6 @@
#include <vector>
#include <string>
#include <unordered_map>
#include <map>
#include <fstream>
#include <filesystem>
@ -77,11 +77,6 @@ static const char * const LLM_KV_QUANTIZE_IMATRIX_DATASET = "quantize.imatrix
static const char * const LLM_KV_QUANTIZE_IMATRIX_N_ENTRIES = "quantize.imatrix.entries_count";
static const char * const LLM_KV_QUANTIZE_IMATRIX_N_CHUNKS = "quantize.imatrix.chunks_count";
// TODO: share with imatrix.cpp
static const char * const LLM_KV_IMATRIX_DATASETS = "imatrix.datasets";
static const char * const LLM_KV_IMATRIX_CHUNK_COUNT = "imatrix.chunk_count";
static const char * const LLM_KV_IMATRIX_CHUNK_SIZE = "imatrix.chunk_size";
static bool striequals(const char * a, const char * b) {
while (*a && *b) {
if (std::tolower(*a) != std::tolower(*b)) {
@ -180,184 +175,84 @@ static void usage(const char * executable) {
exit(1);
}
static int load_legacy_imatrix(const std::string & imatrix_file, std::vector<std::string> & imatrix_datasets, std::unordered_map<std::string, std::vector<float>> & imatrix_data) {
std::ifstream in(imatrix_file.c_str(), std::ios::binary);
if (!in) {
printf("%s: failed to open %s\n",__func__, imatrix_file.c_str());
exit(1);
}
int n_entries;
in.read((char *)&n_entries, sizeof(n_entries));
if (in.fail() || n_entries < 1) {
printf("%s: no data in file %s\n", __func__, imatrix_file.c_str());
exit(1);
}
for (int i = 0; i < n_entries; ++i) {
int len; in.read((char *)&len, sizeof(len));
std::vector<char> name_as_vec(len+1);
in.read((char *)name_as_vec.data(), len);
if (in.fail()) {
printf("%s: failed reading name for entry %d from %s\n", __func__, i+1, imatrix_file.c_str());
exit(1);
}
name_as_vec[len] = 0;
std::string name{name_as_vec.data()};
auto & e = imatrix_data[name];
int ncall;
in.read((char *)&ncall, sizeof(ncall));
int nval;
in.read((char *)&nval, sizeof(nval));
if (in.fail() || nval < 1) {
printf("%s: failed reading number of values for entry %d\n", __func__, i);
imatrix_data = {};
exit(1);
}
e.resize(nval);
in.read((char *)e.data(), nval*sizeof(float));
if (in.fail()) {
printf("%s: failed reading data for entry %d\n", __func__, i);
imatrix_data = {};
exit(1);
}
if (ncall > 0) {
for (auto & v : e) {
v /= ncall;
}
}
if (getenv("LLAMA_TRACE")) {
printf("%s: loaded data (size = %6d, ncall = %6d) for '%s'\n", __func__, int(e.size()), ncall, name.c_str());
}
}
// latest legacy imatrix version contains the dataset filename at the end of the file
int m_last_call = 0;
if (in.peek() != EOF) {
in.read((char *)&m_last_call, sizeof(m_last_call));
int dataset_len;
in.read((char *)&dataset_len, sizeof(dataset_len));
std::vector<char> dataset_as_vec(dataset_len);
in.read(dataset_as_vec.data(), dataset_len);
imatrix_datasets.resize(1);
imatrix_datasets[0].assign(dataset_as_vec.begin(), dataset_as_vec.end());
printf("%s: imatrix dataset='%s'\n", __func__, imatrix_datasets[0].c_str());
}
printf("%s: loaded %d importance matrix entries from %s computed on %d chunks\n", __func__, int(imatrix_data.size()), imatrix_file.c_str(), m_last_call);
return m_last_call;
}
static int load_imatrix(const std::string & imatrix_file, std::vector<std::string> & imatrix_datasets, std::unordered_map<std::string, std::vector<float>> & imatrix_data) {
struct ggml_context * ctx = nullptr;
struct gguf_init_params meta_gguf_params = {
/* .no_alloc = */ false, // the data is needed
/* .ctx = */ &ctx,
};
struct gguf_context * ctx_gguf = gguf_init_from_file(imatrix_file.c_str(), meta_gguf_params);
if (!ctx_gguf) {
fprintf(stderr, "%s: imatrix file '%s' is using old format\n", __func__, imatrix_file.c_str());
return load_legacy_imatrix(imatrix_file, imatrix_datasets, imatrix_data);
}
const int32_t n_entries = gguf_get_n_tensors(ctx_gguf);
if (n_entries < 1) {
fprintf(stderr, "%s: no data in file %s\n", __func__, imatrix_file.c_str());
gguf_free(ctx_gguf);
ggml_free(ctx);
common_imatrix loaded;
if (!common_imatrix_load(imatrix_file, loaded)) {
fprintf(stderr, "%s: failed to load imatrix from '%s'\n", __func__, imatrix_file.c_str());
exit(1);
}
const int dataset_idx = gguf_find_key(ctx_gguf, LLM_KV_IMATRIX_DATASETS);
const int chunk_count_idx = gguf_find_key(ctx_gguf, LLM_KV_IMATRIX_CHUNK_COUNT);
const int chunk_size_idx = gguf_find_key(ctx_gguf, LLM_KV_IMATRIX_CHUNK_SIZE);
if (dataset_idx < 0 || chunk_count_idx < 0 || chunk_size_idx < 0) {
if (!loaded.is_legacy && !loaded.has_metadata) {
fprintf(stderr, "%s: missing imatrix metadata in file %s\n", __func__, imatrix_file.c_str());
gguf_free(ctx_gguf);
ggml_free(ctx);
exit(1);
}
const uint32_t chunk_size = gguf_get_val_u32(ctx_gguf, chunk_size_idx);
const std::string sums_suffix{ ".in_sum2" };
const std::string counts_suffix{ ".counts" };
// Using an ordered map to get a deterministic iteration order.
std::map<std::string, std::pair<struct ggml_tensor *, struct ggml_tensor *>> sums_counts_for;
for (struct ggml_tensor * cur = ggml_get_first_tensor(ctx); cur; cur = ggml_get_next_tensor(ctx, cur)) {
std::string name = cur->name;
if (name.empty()) { continue; }
if (string_remove_suffix(name, sums_suffix)) {
// in_sum2
sums_counts_for[std::move(name)].first = cur;
} else if (string_remove_suffix(name, counts_suffix)) {
// counts
sums_counts_for[std::move(name)].second = cur;
} else {
// ignore other tensors
}
}
for (const auto & sc : sums_counts_for) {
const std::string & name = sc.first;
const struct ggml_tensor * sums = sc.second.first;
const struct ggml_tensor * counts = sc.second.second;
if (!sums || !counts) {
fprintf(stderr, "%s: mismatched sums and counts for %s\n", __func__, name.c_str());
gguf_free(ctx_gguf);
ggml_free(ctx);
exit(1);
}
const int64_t ne0 = sums->ne[0];
const int64_t ne1 = sums->ne[1];
for (const auto & [name, entry] : loaded.entries) {
auto & e = imatrix_data[name];
e.resize(ggml_nelements(sums));
float max_count = 0.0f;
for (int64_t j = 0; j < ne1; ++j) {
const float count = ((const float *) counts->data)[j];
if (count > 0.0f) {
for (int64_t i = 0; i < ne0; ++i) {
e[j*ne0 + i] = ((const float *) sums->data)[j*ne0 + i] / count;
e.resize(entry.sums.size());
if (!loaded.is_legacy) {
// GGUF format: normalize by per-expert counts
const int64_t ncounts = entry.counts.size();
const int64_t ne0 = (int64_t) entry.sums.size() / ncounts;
for (int64_t j = 0; j < ncounts; ++j) {
const float count = (float) entry.counts[j];
if (count > 0.0f) {
for (int64_t i = 0; i < ne0; ++i) {
e[j*ne0 + i] = entry.sums[j*ne0 + i] / count;
}
} else {
for (int64_t i = 0; i < ne0; ++i) {
e[j*ne0 + i] = 1;
}
}
}
if (getenv("LLAMA_TRACE")) {
float max_count = 0.0f;
for (int64_t j = 0; j < ncounts; ++j) {
const float count = (float) entry.counts[j];
if (count > max_count) {
max_count = count;
}
}
printf("%s: loaded data (size = %6d, n_tokens = %6d, n_chunks = %6d) for '%s'\n",
__func__, int(e.size()), int(max_count), int(max_count / loaded.chunk_size), name.c_str());
}
} else {
// Legacy format: sums contain (raw/count)*ncall, divide by ncall
const int64_t ncall = entry.counts.empty() ? 0 : entry.counts[0];
if (ncall > 0) {
for (size_t i = 0; i < entry.sums.size(); ++i) {
e[i] = entry.sums[i] / ncall;
}
} else {
// Partial imatrix data, this tensor never got any input during calibration
for (int64_t i = 0; i < ne0; ++i) {
e[j*ne0 + i] = 1;
for (size_t i = 0; i < entry.sums.size(); ++i) {
e[i] = entry.sums[i];
}
}
if (count > max_count) {
max_count = count;
if (getenv("LLAMA_TRACE")) {
printf("%s: loaded data (size = %6d, ncall = %6d) for '%s'\n",
__func__, int(e.size()), int(ncall), name.c_str());
}
}
if (getenv("LLAMA_TRACE")) {
printf("%s: loaded data (size = %6d, n_tokens = %6d, n_chunks = %6d) for '%s'\n", __func__, int(e.size()), int(max_count), int(max_count / chunk_size), name.c_str());
}
imatrix_datasets = std::move(loaded.datasets);
if (!imatrix_datasets.empty()) {
printf("%s: imatrix datasets=['%s'", __func__, imatrix_datasets[0].c_str());
for (size_t i = 1; i < imatrix_datasets.size(); ++i) {
printf(", '%s'", imatrix_datasets[i].c_str());
}
printf("]\n");
}
int m_last_chunk = gguf_get_val_u32(ctx_gguf, chunk_count_idx);
printf("%s: loaded %d importance matrix entries from %s computed on %d chunks\n", __func__, int(imatrix_data.size()), imatrix_file.c_str(), loaded.chunk_count);
int64_t n_datasets = gguf_get_arr_n(ctx_gguf, dataset_idx);
imatrix_datasets.reserve(n_datasets);
for (int64_t i = 0; i < n_datasets; ++i) {
imatrix_datasets.push_back(gguf_get_arr_str(ctx_gguf, dataset_idx, i));
}
printf("%s: imatrix datasets=['%s'", __func__, imatrix_datasets[0].c_str());
for (size_t i = 1; i < imatrix_datasets.size(); ++i) {
printf(", '%s'", imatrix_datasets[i].c_str());
}
printf("]\n");
printf("%s: loaded %d importance matrix entries from %s computed on %d chunks\n", __func__, int(imatrix_data.size()), imatrix_file.c_str(), m_last_chunk);
gguf_free(ctx_gguf);
ggml_free(ctx);
return m_last_chunk;
return loaded.chunk_count;
}
static int prepare_imatrix(const std::string & imatrix_file,