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

#include "models.h"

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);
        // UNUSED:
        // const float freq_base_l  = model.get_rope_freq_base (cparams, il);
        // const float freq_scale_l = model.get_rope_freq_scale(cparams, 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
            auto [Qcur, Kcur, Vcur] = build_qkv(model.layers[il], cur,
                    n_embd_head, n_head, n_head_kv, il);

            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, model.layers[il].wo_s,
                    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);
}