llama-cpp-sys-4 0.2.46

Low Level Bindings to llama.cpp
Documentation 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156

#include "models.h"

llm_build_bert::llm_build_bert(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());

    ggml_tensor * cur;
    ggml_tensor * inpL;
    ggml_tensor * inp_pos = nullptr;

    if (model.arch != LLM_ARCH_JINA_BERT_V2) {
        inp_pos = build_inp_pos();
    }

    // construct input embeddings (token, type, position)
    inpL = build_inp_embd(model.tok_embd);

    // token types are hardcoded to zero ("Sentence A")
    if (model.type_embd) {
        ggml_tensor * type_row0 = ggml_view_1d(ctx0, model.type_embd, n_embd, 0);
        inpL                    = ggml_add(ctx0, inpL, type_row0);
    }
    if (model.arch == LLM_ARCH_BERT) {
        inpL = ggml_add(ctx0, ggml_get_rows(ctx0, model.pos_embd, inp_pos), inpL);
    }
    cb(inpL, "inp_embd", -1);

    // embed layer norm
    inpL = build_norm(inpL, model.tok_norm, model.tok_norm_b, LLM_NORM, 0);
    cb(inpL, "inp_norm", 0);

    auto * inp_attn = build_attn_inp_no_cache();

    ggml_tensor * inp_out_ids = build_inp_out_ids();

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

        {
            auto [Qcur, Kcur, Vcur] = build_qkv(model.layers[il], cur,
                    n_embd_head, n_head, n_head_kv, il);

            if (model.layers[il].attn_q_norm) {
                Qcur = ggml_reshape_2d(ctx0, Qcur, n_embd_head * n_head, n_tokens);

                Qcur = build_norm(Qcur, model.layers[il].attn_q_norm, model.layers[il].attn_q_norm_b, LLM_NORM, il);

                Qcur = ggml_reshape_3d(ctx0, Qcur, n_embd_head, n_head, n_tokens);
            }

            if (model.layers[il].attn_k_norm) {
                Kcur = ggml_reshape_2d(ctx0, Kcur, n_embd_head * n_head_kv, n_tokens);

                Kcur = build_norm(Kcur, model.layers[il].attn_k_norm, model.layers[il].attn_k_norm_b, LLM_NORM, il);

                Kcur = ggml_reshape_3d(ctx0, Kcur, n_embd_head, n_head_kv, n_tokens);
            }

            // RoPE
            if (model.arch == LLM_ARCH_NOMIC_BERT || model.arch == LLM_ARCH_NOMIC_BERT_MOE ||
                model.arch == LLM_ARCH_JINA_BERT_V3) {
                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, model.layers[il].bo, model.layers[il].wo_s,
                    Qcur, Kcur, Vcur, nullptr, nullptr, nullptr, 1.0f / sqrtf(float(n_embd_head)), il);
            cb(cur, "kqv_out", 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);
        }

        // re-add the layer input
        cur = ggml_add(ctx0, cur, inpL);

        // attention layer norm
        cur = build_norm(cur, model.layers[il].attn_out_norm, model.layers[il].attn_out_norm_b, LLM_NORM, il);

        if (model.layers[il].attn_norm_2 != nullptr) {
            cur = ggml_add(ctx0, cur, inpL);  // re-add the layer input
            cur = build_norm(cur, model.layers[il].attn_norm_2, model.layers[il].attn_norm_2_b, LLM_NORM, il);
        }

        ggml_tensor * ffn_inp = cur;
        cb(ffn_inp, "ffn_inp", il);

        // feed-forward network
        if (hparams.moe_every_n_layers > 0 && il % hparams.moe_every_n_layers == 1) {
            // MoE branch
            cur = build_moe_ffn(cur,
                    model.layers[il].ffn_gate_inp,
                    model.layers[il].ffn_up_exps,
                    nullptr,
                    model.layers[il].ffn_down_exps,
                    nullptr,
                    hparams.n_expert, hparams.n_expert_used,
                    LLM_FFN_GELU, false,
                    hparams.expert_weights_scale,
                    LLAMA_EXPERT_GATING_FUNC_TYPE_SOFTMAX,
                    il);
            cb(cur, "ffn_moe_out", il);
        } else if (model.arch == LLM_ARCH_BERT || model.arch == LLM_ARCH_NOMIC_BERT_MOE ||
                   model.arch == LLM_ARCH_JINA_BERT_V3) {
            cur = build_ffn(cur,
                    model.layers[il].ffn_up, model.layers[il].ffn_up_b, NULL,
                    NULL, NULL, NULL,
                    model.layers[il].ffn_down, model.layers[il].ffn_down_b, NULL, NULL,
                    LLM_FFN_GELU, LLM_FFN_SEQ, il);
            cb(cur, "ffn_out", il);
        } else if (model.arch == LLM_ARCH_JINA_BERT_V2) {
            const bool up_contains_gate = !model.layers[il].ffn_gate && model.layers[il].ffn_up->ne[1] != hparams.n_ff();
            auto type_op = up_contains_gate ? LLM_FFN_GEGLU : LLM_FFN_GELU;
            cur = build_ffn(cur,
                    model.layers[il].ffn_up, model.layers[il].ffn_up_b, NULL,
                    model.layers[il].ffn_gate, NULL, NULL,
                    model.layers[il].ffn_down, model.layers[il].ffn_down_b, NULL, NULL,
                    type_op, LLM_FFN_PAR, il);
            cb(cur, "ffn_out", il);
        } else {
            cur = build_ffn(cur,
                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);
        }

        // attentions bypass the intermediate layer
        cur = ggml_add(ctx0, cur, ffn_inp);

        // output layer norm
        cur = build_norm(cur, model.layers[il].layer_out_norm, model.layers[il].layer_out_norm_b, LLM_NORM, il);

        // input for next layer
        inpL = cur;
    }

    cur = inpL;

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

    ggml_build_forward_expand(gf, cur);
}