Move duplicated imatrix code into single common imatrix-loader.cpp (#22445)

* Deduplicate imatrix loading code

* Add back LLAMA_TRACE, early exit on quantize missing metadata
This commit is contained in:
Bartowski
2026-06-04 17:45:40 +02:00
committed by GitHub
parent 21444c822e
commit e7bcf1c3a8
5 changed files with 303 additions and 359 deletions
+26
View File
@@ -0,0 +1,26 @@
#pragma once
#include <cstdint>
#include <map>
#include <string>
#include <vector>
inline constexpr const char * LLM_KV_IMATRIX_DATASETS = "imatrix.datasets";
inline constexpr const char * LLM_KV_IMATRIX_CHUNK_COUNT = "imatrix.chunk_count";
inline constexpr const char * LLM_KV_IMATRIX_CHUNK_SIZE = "imatrix.chunk_size";
struct common_imatrix_entry {
std::vector<float> sums;
std::vector<int64_t> counts;
};
struct common_imatrix {
std::map<std::string, common_imatrix_entry> entries;
std::vector<std::string> datasets;
int32_t chunk_count = 0;
int32_t chunk_size = 0;
bool is_legacy = false;
bool has_metadata = false;
};
bool common_imatrix_load(const std::string & fname, common_imatrix & imatrix);