llama.cpp/src/models/glm4.cpp

#include "models.h"



llm_build_glm4::llm_build_glm4(const llama_model & model, const llm_graph_params & params) : llm_graph_context(params) {
    const int64_t n_embd_head = hparams.n_embd_head_v;
    const int64_t n_embd_gqa  = hparams.n_embd_v_gqa();

    GGML_ASSERT(n_embd_head == hparams.n_embd_head_k);

    ggml_tensor * cur;
    ggml_tensor * inpL;

    inpL = build_inp_embd(model.tok_embd);

    // 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;

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

        // self-attention
        {
            ggml_tensor * Qcur = nullptr;
            ggml_tensor * Kcur = nullptr;
            ggml_tensor * Vcur = nullptr;

            if (model.layers[il].wqkv == nullptr) {
                Qcur = build_lora_mm(model.layers[il].wq, cur);
                if (model.layers[il].bq) {
                    Qcur = ggml_add(ctx0, Qcur, model.layers[il].bq);
                }
                Kcur = build_lora_mm(model.layers[il].wk, cur);
                if (model.layers[il].bk) {
                    Kcur = ggml_add(ctx0, Kcur, model.layers[il].bk);
                }
                Vcur = build_lora_mm(model.layers[il].wv, cur);
                if (model.layers[il].bv) {
                    Vcur = ggml_add(ctx0, Vcur, model.layers[il].bv);
                }
                Qcur = ggml_reshape_3d(ctx0, Qcur, n_embd_head, n_head, n_tokens);
                Kcur = ggml_reshape_3d(ctx0, Kcur, n_embd_head, n_head_kv, n_tokens);
                Vcur = ggml_reshape_3d(ctx0, Vcur, n_embd_head, n_head_kv, n_tokens);
            } else {
                cur = build_lora_mm(model.layers[il].wqkv, cur);
                cb(cur, "wqkv", il);
                if (model.layers[il].bqkv) {
                    cur = ggml_add(ctx0, cur, model.layers[il].bqkv);
                    cb(cur, "bqkv", il);
                }
                Qcur = ggml_view_3d(ctx0, cur, n_embd_head, n_head, n_tokens, n_embd_head * sizeof(float), cur->nb[1],
                                    0 * sizeof(float) * (n_embd));
                Kcur = ggml_view_3d(ctx0, cur, n_embd_head, n_head_kv, n_tokens, n_embd_head * sizeof(float),
                                    cur->nb[1], 1 * sizeof(float) * (n_embd));
                Vcur = ggml_view_3d(ctx0, cur, n_embd_head, n_head_kv, n_tokens, n_embd_head * sizeof(float),
                                    cur->nb[1], 1 * sizeof(float) * (n_embd + n_embd_gqa));
            }
            Qcur = ggml_rope_ext(ctx0, Qcur, inp_pos, nullptr, n_rot, rope_type, n_ctx_orig, freq_base, freq_scale,
                                 ext_factor, attn_factor, beta_fast, beta_slow);

            Kcur = ggml_rope_ext(ctx0, Kcur, inp_pos, nullptr, n_rot, rope_type, n_ctx_orig, freq_base, freq_scale,
                                 ext_factor, attn_factor, beta_fast, beta_slow);

            cb(Qcur, "Qcur", il);
            cb(Kcur, "Kcur", il);
            cb(Vcur, "Vcur", il);

            cur = build_attn(inp_attn,
                    model.layers[il].wo, NULL,
                    Qcur, Kcur, Vcur, nullptr, nullptr, nullptr, 1.0f / sqrtf(float(n_embd_head)), il);
        }
        if (il == n_layer - 1 && inp_out_ids) {
            cur   = ggml_get_rows(ctx0, cur, inp_out_ids);
            inpSA = ggml_get_rows(ctx0, inpSA, inp_out_ids);
        }
        // Post-attention norm (new!)
        cur = build_norm(cur, model.layers[il].attn_post_norm, NULL, LLM_NORM_RMS, il);
        cb(cur, "post_attn_norm", il);

        // Add the input (residual connection after post-attention norm)
        ggml_tensor * ffn_inp = ggml_add(ctx0, cur, inpSA);
        cb(ffn_inp, "ffn_inp", il);

        // FF
        {
            // Pre-MLP norm
            cur = build_norm(ffn_inp, model.layers[il].ffn_norm, NULL, LLM_NORM_RMS, il);
            cb(cur, "ffn_norm", il);

            // MLP
            cur = build_ffn(cur,
                    model.layers[il].ffn_up, NULL, NULL,
                    NULL, NULL, NULL,
                    model.layers[il].ffn_down, NULL, NULL,
                    NULL, LLM_FFN_SWIGLU, LLM_FFN_SEQ, il);
            cb(cur, "ffn_out", il);

            // Post-MLP norm
            cur = build_norm(cur, model.layers[il].ffn_post_norm, NULL, LLM_NORM_RMS, il);
            cb(cur, "post_mlp_norm", il);
        }
        // Add residual connection after post-MLP norm
        inpL = ggml_add(ctx0, cur, ffn_inp);
        cb(inpL, "l_out", il);
    }
    // Final norm
    cur = build_norm(inpL, model.output_norm, NULL, LLM_NORM_RMS, -1);

    cb(cur, "result_norm", -1);
    res->t_embd = cur;

    // Output projection
    cur = build_lora_mm(model.output, cur);

    cb(cur, "result_output", -1);
    res->t_logits = cur;

    ggml_build_forward_expand(gf, cur);
}