Function build_attn_inp_k_impl

subprojects/llama.cpp/src/llama-graph.cpp:1889–1914

}

static std::unique_ptr<llm_graph_input_attn_k> build_attn_inp_k_impl(
           ggml_context * ctx0,
     const llama_ubatch & ubatch,
    const llama_hparams & hparams,
    const llama_cparams & cparams,
    const llama_kv_cache_context * mctx_cur) {

    auto inp = std::make_unique<llm_graph_input_attn_k>(hparams, cparams, mctx_cur);

    {
        GGML_ASSERT(hparams.swa_type == LLAMA_SWA_TYPE_NONE && "Use llama_kv_cache_iswa for SWA");

        const auto n_kv     = mctx_cur->get_n_kv();
        const auto n_tokens = ubatch.n_tokens;
        const auto n_stream = cparams.kv_unified ? 1 : ubatch.n_seqs_unq;

        inp->self_k_idxs = mctx_cur->build_input_k_idxs(ctx0, ubatch);

        inp->self_kq_mask = ggml_new_tensor_4d(ctx0, GGML_TYPE_F32, n_kv, n_tokens/n_stream, 1, n_stream);
        ggml_set_input(inp->self_kq_mask);

        inp->self_kq_mask_cnv = cparams.flash_attn ? ggml_cast(ctx0, inp->self_kq_mask, GGML_TYPE_F16) : inp->self_kq_mask;
    }

    return inp;
}

llm_graph_input_attn_k * llm_graph_context::build_attn_inp_k() const {
    const auto * mctx_cur = static_cast<const llama_kv_cache_context *>(mctx);