Function load_imatrix

tools/quantize/quantize.cpp:250–362

}

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);
        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) {
        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;