Function llama_get_state_size

llama.cpp:10164–10192

Returns the *maximum* size of the state

// Returns the *maximum* size of the state
size_t llama_get_state_size(const struct llama_context * ctx) {
    // we don't know size of rng until we actually serialize it. so reserve more than enough memory for its serialized state.
    // for reference, std::mt19937(1337) serializes to 6701 bytes.
    const size_t s_rng_size        = sizeof(size_t);
    const size_t s_rng             = LLAMA_MAX_RNG_STATE;
    const size_t s_logits_capacity = sizeof(size_t);
    const size_t s_logits_size     = sizeof(size_t);
    const size_t s_logits          = ctx->logits.capacity() * sizeof(float);
    const size_t s_embedding_size  = sizeof(size_t);
    const size_t s_embedding       = ctx->embedding.size() * sizeof(float);
    const size_t s_kv_size         = sizeof(size_t);
    const size_t s_kv_ntok         = sizeof(int);
    const size_t s_kv              = ctx->kv_self.buf.size;

    const size_t s_total = (
        + s_rng_size
        + s_rng
        + s_logits_capacity
        + s_logits_size
        + s_logits
        + s_embedding_size
        + s_embedding
        + s_kv_size
        + s_kv_ntok
        + s_kv
    );

    return s_total;
}

// llama_context_data
struct llama_data_context {