Function llama_kv_cache_seq_shift

llama.cpp:1819–1847

}

static void llama_kv_cache_seq_shift(
        struct llama_kv_cache & cache,
                 llama_seq_id   seq_id,
                    llama_pos   p0,
                    llama_pos   p1,
                    llama_pos   delta) {
    uint32_t new_head = cache.size;

    if (p0 < 0) p0 = 0;
    if (p1 < 0) p1 = std::numeric_limits<llama_pos>::max();

    for (uint32_t i = 0; i < cache.size; ++i) {
        if (cache.cells[i].has_seq_id(seq_id) && cache.cells[i].pos >= p0 && cache.cells[i].pos < p1) {
            cache.has_shift = true;
            cache.cells[i].pos   += delta;
            cache.cells[i].delta += delta;

            if (cache.cells[i].pos < 0) {
                cache.cells[i].pos = -1;
                cache.cells[i].seq_id.clear();
                if (new_head == cache.size) new_head = i;
            }
        }
    }

    // If we freed up a slot, set head to it so searching can start there.
    // Otherwise we just start the next search from the beginning.
    cache.head = new_head != cache.size ? new_head : 0;
}

//
// model loading and saving