Method get_v

subprojects/llama.cpp/src/llama-kv-cache.cpp:1036–1066

}

ggml_tensor * llama_kv_cache::get_v(ggml_context * ctx, int32_t il, uint32_t n_kv, const slot_info & sinfo) const {
    const int32_t ikv = map_layer_ids.at(il);

    auto * v = layers[ikv].v;

    const uint64_t kv_size      = get_size();
    const uint64_t n_embd_v_gqa = v->ne[0];

    // [TAG_V_CACHE_VARIABLE]
    assert(n_embd_v_gqa >= hparams.n_embd_v_gqa(il));

    const uint32_t ns = sinfo.s1 - sinfo.s0 + 1;

    if (!v_trans) {
        // note: v->nb[1] <= v->nb[2]
        return ggml_view_4d(ctx, v,
                hparams.n_embd_head_v, hparams.n_head_kv(il), n_kv, ns,
                ggml_row_size(v->type, hparams.n_embd_head_v),          // v->nb[1]
                ggml_row_size(v->type, n_embd_v_gqa),                   // v->nb[2]
                ggml_row_size(v->type, n_embd_v_gqa*kv_size),           // v->nb[3]
                ggml_row_size(v->type, n_embd_v_gqa*kv_size)*sinfo.s0);
    }

    // note: v->nb[1] > v->nb[2]
    return ggml_view_4d(ctx, v,
            n_kv, hparams.n_head_kv(il), hparams.n_embd_head_v, ns,
            ggml_row_size(v->type, kv_size*hparams.n_embd_head_v),  // v->nb[1]
            ggml_row_size(v->type, kv_size),                        // v->nb[2]
            ggml_row_size(v->type, kv_size*n_embd_v_gqa),           // v->nb[3]
            ggml_row_size(v->type, kv_size*n_embd_v_gqa)*sinfo.s0);
}

ggml_tensor * llama_kv_cache::cpy_k(ggml_context * ctx, ggml_tensor * k_cur, ggml_tensor * k_idxs, int32_t il, const slot_info & sinfo) const {
    GGML_UNUSED(sinfo);