llama.cpp/src/models/llm_build_cohere2_iswa.cpp

#include "../llama-model.h"
#include "../llama-graph.h"

#include "llm_build_cohere2_iswa.h"
#include <cmath>

llm_build_cohere2_iswa::llm_build_cohere2_iswa(const llama_model & model, const llm_graph_params & params) : llm_graph_context(params) {
    const int64_t n_embd_head = hparams.n_embd_head_v;

    GGML_ASSERT(n_embd_head == hparams.n_embd_head_k);

    const float f_logit_scale = hparams.f_logit_scale;

    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_iswa();

    ggml_tensor * inp_out_ids = build_inp_out_ids();

    for (int il = 0; il < n_layer; ++il) {
        const bool is_swa = hparams.is_swa(il);

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

        // self-attention
        {
            // rope freq factors for 128k context
            ggml_tensor * rope_factors = model.get_rope_factors(cparams, il);

            // compute Q and K and RoPE them
            ggml_tensor * Qcur = build_lora_mm(model.layers[il].wq, cur);
            cb(Qcur, "Qcur", il);
            if (model.layers[il].bq) {
                Qcur = ggml_add(ctx0, Qcur, model.layers[il].bq);
                cb(Qcur, "Qcur", il);
            }

            ggml_tensor * Kcur = build_lora_mm(model.layers[il].wk, cur);
            cb(Kcur, "Kcur", il);
            if (model.layers[il].bk) {
                Kcur = ggml_add(ctx0, Kcur, model.layers[il].bk);
                cb(Kcur, "Kcur", il);
            }

            ggml_tensor * Vcur = build_lora_mm(model.layers[il].wv, cur);
            cb(Vcur, "Vcur", il);
            if (model.layers[il].bv) {
                Vcur = ggml_add(ctx0, Vcur, model.layers[il].bv);
                cb(Vcur, "Vcur", il);
            }

            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);

            if (is_swa) {
                Qcur = ggml_rope_ext(
                        ctx0, Qcur, inp_pos, rope_factors,
                        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, rope_factors,
                        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, model.layers[il].bo,
                    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);
            inpL    = ggml_get_rows(ctx0, inpL, inp_out_ids);
            ffn_inp = ggml_get_rows(ctx0, ffn_inp, inp_out_ids);
        }

        ggml_tensor * attn_out = cur;

        // feed-forward network
        {
            cur = build_ffn(ffn_inp, model.layers[il].ffn_up, NULL, NULL, model.layers[il].ffn_gate,
                    NULL, NULL, model.layers[il].ffn_down, NULL, NULL, NULL, LLM_FFN_SILU, LLM_FFN_PAR,
                    il);
            cb(cur, "ffn_out", il);
        }

        // add together residual + FFN + self-attention
        cur = ggml_add(ctx0, cur, inpL);
        cur = ggml_add(ctx0, cur, attn_out);

        cur = build_cvec(cur, il);
        cb(cur, "l_out", il);

        // input for next layer
        inpL = cur;
    }

    cur = inpL;

    cur = build_norm(cur, model.output_norm, NULL, LLM_NORM, -1);

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

    // lm_head
    cur = build_lora_mm(model.output, cur);

    if (f_logit_scale) {
        cur = ggml_scale(ctx0, cur, f_logit_scale);
    }

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

    ggml_build_forward_expand(gf, cur);
}