Function llama_copy_state_data_internal

llama.cpp:10247–10360

copy state data into either a buffer or file depending on the passed in context * * file context: * llama_file file("/path", "wb"); * llama_data_file_context data_ctx(&file); * llama_copy_state_data(ctx, &data_ctx); * * buffer context: * std::vector buf(max_size, 0); * llama_data_buffer_context data_ctx(&buf.data()); * llama_copy_state_data(ctx, &data_ctx); * */

 *
*/
static void llama_copy_state_data_internal(struct llama_context * ctx, llama_data_context * data_ctx) {
    // copy rng
    {
        std::stringstream rng_ss;
        rng_ss << ctx->rng;

        const size_t rng_size = rng_ss.str().size();
        char rng_buf[LLAMA_MAX_RNG_STATE];

        memset(&rng_buf[0], 0, LLAMA_MAX_RNG_STATE);
        memcpy(&rng_buf[0], rng_ss.str().data(), rng_ss.str().size());

        data_ctx->write(&rng_size,   sizeof(rng_size));
        data_ctx->write(&rng_buf[0], LLAMA_MAX_RNG_STATE);
    }

    // copy logits
    {
        const size_t logits_cap  = ctx->logits.capacity();
        const size_t logits_size = ctx->logits.size();

        data_ctx->write(&logits_cap,  sizeof(logits_cap));
        data_ctx->write(&logits_size, sizeof(logits_size));

        if (logits_size) {
            data_ctx->write(ctx->logits.data(), logits_size * sizeof(float));
        }

        // If there is a gap between the size and the capacity, write padding
        size_t padding_size = (logits_cap - logits_size) * sizeof(float);
        if (padding_size > 0) {
            std::vector<uint8_t> padding(padding_size, 0); // Create a buffer filled with zeros
            data_ctx->write(padding.data(), padding_size);
        }
    }

    // copy embeddings
    {
        const size_t embedding_size = ctx->embedding.size();

        data_ctx->write(&embedding_size, sizeof(embedding_size));

        if (embedding_size) {
            data_ctx->write(ctx->embedding.data(), embedding_size * sizeof(float));
        }
    }

    // copy kv cache
    {
        const auto & kv_self = ctx->kv_self;
        const auto & hparams = ctx->model.hparams;
        const auto & cparams = ctx->cparams;

        const auto   n_layer = hparams.n_layer;
        const auto   n_embd  = hparams.n_embd_gqa();
        const auto   n_ctx   = cparams.n_ctx;

        const size_t   kv_buf_size = kv_self.buf.size;