Method load_imatrix

subprojects/llama.cpp/tools/imatrix/imatrix.cpp:716–829

Using GGUF as the file format, for greater extensibility

// Using GGUF as the file format, for greater extensibility
bool IMatrixCollector::load_imatrix(const char * file_name) {
    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(file_name, meta_gguf_params);
    if (!ctx_gguf) {
        return this->load_imatrix_legacy(file_name);
    }
    const int32_t n_entries = gguf_get_n_tensors(ctx_gguf);
    if (n_entries < 1) {
        LOG_ERR("%s: no data in file %s\n", __func__, file_name);
        gguf_free(ctx_gguf);
        ggml_free(ctx);
        return false;
    }

    const int64_t datasets_key = gguf_find_key(ctx_gguf, LLM_KV_IMATRIX_DATASETS);
    if (datasets_key != -1 && gguf_get_arr_type(ctx_gguf, datasets_key) == GGUF_TYPE_STRING) {
        const int64_t n = gguf_get_arr_n(ctx_gguf, datasets_key);
        m_datasets.reserve(m_datasets.size() + n);
        for (int64_t i = 0; i < n; ++i) {
            m_datasets.push_back(gguf_get_arr_str(ctx_gguf, datasets_key, i));
        }
    }

    const std::string in_sum2_suffix{ ".in_sum2" };
    const std::string counts_suffix{ ".counts" };

    // Could re-use m_stats instead, but this allows
    // checking for completeness of *each* loaded imatrix file
    // and also makes it easier to re-use a similar implementation in quantize.cpp
    // 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, in_sum2_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 * in_sum2 = sc.second.first;
        const struct ggml_tensor * counts  = sc.second.second;

        if (!in_sum2 || !counts) {