Function common_debug_cb_eval

subprojects/llama.cpp/common/debug.cpp:113–159

 * @return true to receive data or continue the graph, false otherwise
 */
template <bool abort_on_nan> bool common_debug_cb_eval(struct ggml_tensor * t, bool ask, void * user_data) {
    auto * cb_data = (base_callback_data *) user_data;

    const struct ggml_tensor * src0 = t->src[0];
    const struct ggml_tensor * src1 = t->src[1];

    if (ask) {
        return true;  // Always retrieve data
    }

    bool matches_filter = cb_data->tensor_filters.empty();

    if (!matches_filter) {
        for (const auto & filter : cb_data->tensor_filters) {
            if (std::regex_search(t->name, filter)) {
                matches_filter = true;
                break;
            }
        }
    }

    char src1_str[128] = { 0 };
    if (src1) {
        snprintf(src1_str, sizeof(src1_str), "%s{%s}", src1->name, common_ggml_ne_string(src1).c_str());
    }

    if (matches_filter) {
        LOG_ERR("%s: %24s = (%s) %10s(%s{%s}, %s}) = {%s}\n", __func__, t->name, ggml_type_name(t->type),
                ggml_op_desc(t), src0->name, common_ggml_ne_string(src0).c_str(), src1 ? src1_str : "",
                common_ggml_ne_string(t).c_str());
    }

    const bool is_host = ggml_backend_buffer_is_host(t->buffer);

    if (!is_host) {
        auto n_bytes = ggml_nbytes(t);
        cb_data->data.resize(n_bytes);
        ggml_backend_tensor_get(t, cb_data->data.data(), 0, n_bytes);
    }

    if (!ggml_is_quantized(t->type) && matches_filter) {
        uint8_t * data = is_host ? (uint8_t *) t->data : cb_data->data.data();
        common_debug_print_tensor<abort_on_nan>(data, t->type, t->ne, t->nb, 3);
    }

    return true;
}

// Explicit template instantiations
template bool common_debug_cb_eval<false>(ggml_tensor *, bool, void *);