solar.cpp

#include "models.h"

llm_build_solar::llm_build_solar(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_ASSERT(n_embd_head == hparams.n_rot);

        struct ggml_tensor * cur;
        struct ggml_tensor * inpL;

        inpL = build_inp_embd(model.tok_embd);

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

        // KQ_mask (mask for 1 head, it will be broadcasted to all heads)
        auto * inp_attn = build_attn_inp_kv();

        const float kq_scale = hparams.f_attention_scale == 0.0f ? 1.0f/sqrtf(float(n_embd_head)) : hparams.f_attention_scale;

        struct ggml_tensor * bskcn_1;
        struct ggml_tensor * bskcn_2;

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

            if (hparams.n_bskcn(0, il)) {
                bskcn_1 = inpSA;
            }

            if (hparams.n_bskcn(1, il)) {
                bskcn_2 = inpSA;
            }

            if (hparams.n_bskcn(2, il)) {
                inpSA = ggml_add(
                   ctx0,
                   ggml_mul(ctx0, bskcn_1, ggml_view_1d(ctx0, model.layers[il].bskcn_tv, 1, 0)),
                   ggml_mul(ctx0, inpSA, ggml_view_1d(ctx0, model.layers[il].bskcn_tv, 1, ggml_element_size(model.layers[il].bskcn_tv))));
            }

            if (hparams.n_bskcn(3, il)) {
                inpSA = ggml_add(
                   ctx0,
                   ggml_mul(ctx0, bskcn_2, ggml_view_1d(ctx0, model.layers[il].bskcn_tv, 1, 0)),
                   ggml_mul(ctx0, inpSA, ggml_view_1d(ctx0, model.layers[il].bskcn_tv, 1, ggml_element_size(model.layers[il].bskcn_tv))));
            }

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

            // self-attention
            {
                // rope freq factors for llama3; may return nullptr for llama2 and other models
                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);

                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, kq_scale, il);
                cb(cur, "attn_out", il);
            }

            if (il == n_layer - 1) {
                // skip computing output for unused tokens
                ggml_tensor * inp_out_ids = build_inp_out_ids();
                cur   = ggml_get_rows(ctx0,   cur, inp_out_ids);
                inpSA = ggml_get_rows(ctx0, inpSA, inp_out_ids);
            }

            ggml_tensor * ffn_inp = ggml_add(ctx0, cur, inpSA);
            cb(ffn_inp, "ffn_inp", il);

            // feed-forward network
            cur = build_norm(ffn_inp,
                    model.layers[il].ffn_norm, NULL,
                    LLM_NORM_RMS, il);
            cb(cur, "ffn_norm", il);

            cur = build_ffn(cur,
                    model.layers[il].ffn_up,   model.layers[il].ffn_up_b,   NULL,
                    model.layers[il].ffn_gate, model.layers[il].ffn_gate_b, NULL,
                    model.layers[il].ffn_down, model.layers[il].ffn_down_b, NULL,
                    NULL,
                    LLM_FFN_SILU, LLM_FFN_PAR, il);
            cb(cur, "ffn_out", il);

            cur = ggml_add(ctx0, cur, ffn_inp);
            cb(cur, "ffn_out", il);

            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_RMS, -1);

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

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

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

        ggml_build_forward_expand(gf, cur);
}