Method llm_build_minicpm3

subprojects/llama.cpp/src/models/minicpm3.cpp:3–200

#include "models.h"

llm_build_minicpm3::llm_build_minicpm3(const llama_model & model, const llm_graph_params & params) : llm_graph_context(params) {
    //TODO: if the model varies, these parameters need to be read from the model
    const int64_t n_embd_base = 256;
    const float scale_embd  = 12.0f;
    const float scale_depth = 1.4f;
    const float kq_scale = 1.0f / sqrtf(float(hparams.n_embd_head_k));

    const uint32_t n_embd_head_qk_rope = hparams.n_rot;
    const uint32_t n_embd_head_qk_nope = hparams.n_embd_head_k - hparams.n_rot;

    const uint32_t kv_lora_rank = hparams.n_lora_kv;

    ggml_tensor * cur;
    ggml_tensor * inpL;

    inpL = build_inp_embd(model.tok_embd);

    // scale the input embeddings
    inpL = ggml_scale(ctx0, inpL, scale_embd);
    cb(inpL, "inp_scaled", -1);

    // inp_pos - contains the positions
    ggml_tensor * inp_pos = build_inp_pos();

    auto * inp_attn = build_attn_inp_kv();

    ggml_tensor * inp_out_ids = build_inp_out_ids();

    for (int il = 0; il < n_layer; ++il) {
        ggml_tensor * inpSA = inpL;

        ggml_tensor * rope_factors = model.get_rope_factors(cparams, il);

        // norm
        cur = build_norm(inpL,
                model.layers[il].attn_norm, NULL,
                LLM_NORM_RMS, il);
        cb(cur, "attn_norm", il);

        // self_attention
        {
            ggml_tensor * q = NULL;
            // {n_embd, q_lora_rank} * {n_embd, n_tokens} -> {q_lora_rank, n_tokens}
            q = ggml_mul_mat(ctx0, model.layers[il].wq_a, cur);
            cb(q, "q", il);

            q = build_norm(q,
                    model.layers[il].attn_q_a_norm, NULL,
                    LLM_NORM_RMS, il);
            cb(q, "q", il);

            // {q_lora_rank, n_head * hparams.n_embd_head_k} * {q_lora_rank, n_tokens} -> {n_head * hparams.n_embd_head_k, n_tokens}
            q = ggml_mul_mat(ctx0, model.layers[il].wq_b, q);
            cb(q, "q", il);

            // split into {n_head * n_embd_head_qk_nope, n_tokens}
            ggml_tensor * q_nope = ggml_view_3d(ctx0, q, n_embd_head_qk_nope, n_head, n_tokens,
                    ggml_row_size(q->type, hparams.n_embd_head_k),