Method state_read_meta

subprojects/llama.cpp/src/llama-kv-cache.cpp:1865–1968

}

bool llama_kv_cache::state_read_meta(llama_io_read_i & io, uint32_t strm, uint32_t cell_count, slot_info & sinfo, llama_seq_id dest_seq_id) {
    auto & cells = v_cells[strm];
    auto & head  = v_heads[strm];

    if (dest_seq_id != -1) {
        // single sequence
        seq_rm(dest_seq_id, -1, -1);

        llama_batch_allocr balloc(hparams.n_pos_per_embd());

        llama_ubatch ubatch = balloc.ubatch_reserve(cell_count, 1);

        ubatch.seq_id_unq[0] = dest_seq_id;

        for (uint32_t i = 0; i < cell_count; ++i) {
            llama_pos pos;
            uint32_t n_seq_id;

            io.read_to(&pos,      sizeof(pos));
            io.read_to(&n_seq_id, sizeof(n_seq_id));

            if (n_seq_id != 1) {
                LLAMA_LOG_ERROR("%s: invalid seq_id-agnostic kv cell\n", __func__);
                return false;
            }

            // read the sequence id, but directly discard it - we will use dest_seq_id instead
            {
                llama_seq_id seq_id;
                io.read_to(&seq_id, sizeof(seq_id));
            }

            ubatch.pos[i]      = pos;
            ubatch.n_seq_id[i] = n_seq_id;
            ubatch.seq_id[i]   = &dest_seq_id;
        }

        sinfo = find_slot(ubatch, false);
        if (sinfo.empty()) {
            LLAMA_LOG_ERROR("%s: failed to find available cells in kv cache\n", __func__);
            return false;
        }

        // TODO: we cannot yet restore llama_kv_cell_ext as the apply_ubatch() does not support it yet
        //       see: https://github.com/ggml-org/llama.cpp/pull/16825#issuecomment-3460868350
        apply_ubatch(sinfo, ubatch);

        LLAMA_LOG_DEBUG("%s: cell_count = %d, dest_seq_id = %d\n", __func__, cell_count, dest_seq_id);

        // DEBUG CHECK: verify that all cells were allocated and have correct seq_id and pos values
        GGML_ASSERT(sinfo.n_stream() == 1);
        GGML_ASSERT(sinfo.idxs[0].size() == cell_count);
        for (uint32_t i = 0; i < cell_count; ++i) {
            const uint32_t idx = sinfo.idxs[0][i];
            GGML_ASSERT(cells.pos_get(idx) == ubatch.pos[i]);
            GGML_ASSERT(cells.seq_has(idx, dest_seq_id));
        }
    } else {