whispercpp 1.3.5 → 1.3.7

data/ext/sources/examples/talk-llama/models/cogvlm.cpp

@@ -1,102 +0,0 @@
-#include "models.h"
-
-llm_build_cogvlm::llm_build_cogvlm(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 float   kq_scale    = 1.0f / sqrtf(float(n_embd_head));
-
-    GGML_ASSERT(n_embd_head == hparams.n_embd_head_k);
-    GGML_ASSERT(n_embd_head == hparams.n_rot);
-
-    ggml_tensor * inpL;
-    ggml_tensor * cur;
-
-    inpL = build_inp_embd(model.tok_embd);
-
-    ggml_tensor * inp_pos = build_inp_pos();
-
-    auto * inp_attn = build_attn_inp_kv();
-
-    // check ubatch to see if we have input tokens (text)
-    // or an input embedding vector (image)
-    bool is_text;
-    if (ubatch.token) {
-        is_text = true;
-    } else {
-        is_text = false;
-    }
-
-    for (int il = 0; il < n_layer; ++il) {
-        // get either the text or image weight tensors
-        ggml_tensor *wqkv, *wo;
-        ggml_tensor *ffn_gate, *ffn_down, *ffn_up;
-
-        if (is_text) {
-            wqkv     = model.layers[il].wqkv;
-            wo       = model.layers[il].wo;
-            ffn_gate = model.layers[il].ffn_gate;
-            ffn_down = model.layers[il].ffn_down;
-            ffn_up   = model.layers[il].ffn_up;
-        } else {
-            wqkv     = model.layers[il].visexp_attn_wqkv;
-            wo       = model.layers[il].visexp_attn_wo;
-            ffn_gate = model.layers[il].visexp_ffn_gate;
-            ffn_down = model.layers[il].visexp_ffn_down;
-            ffn_up   = model.layers[il].visexp_ffn_up;
-        }
-
-        ggml_tensor * inpSA = inpL;
-        cur = build_norm(inpSA, model.layers[il].attn_norm, NULL, LLM_NORM_RMS, il);
-
-        // build self attention
-        {
-            ggml_tensor * qkv = build_lora_mm(wqkv, cur);
-
-            // split qkv into Q, K, V along the first dimension
-            ggml_tensor * Qcur =
-                ggml_view_3d(ctx0, qkv, n_embd_head, n_head, n_tokens, n_embd_head * sizeof(float), qkv->nb[1], 0);
-            ggml_tensor * Kcur = ggml_view_3d(ctx0, qkv, n_embd_head, n_head_kv, n_tokens, n_embd_head * sizeof(float),
-                                              qkv->nb[1], n_embd * ggml_element_size(qkv));
-            ggml_tensor * Vcur = ggml_view_3d(ctx0, qkv, n_embd_head, n_head_kv, n_tokens, n_embd_head * sizeof(float),
-                                              qkv->nb[1], 2 * n_embd * ggml_element_size(qkv));
-
-            Qcur = ggml_rope(ctx0, Qcur, inp_pos, n_embd_head, rope_type);
-            Kcur = ggml_rope(ctx0, Kcur, inp_pos, n_embd_head, rope_type);
-
-            cur = build_attn(inp_attn,
-                wo, nullptr,
-                Qcur, Kcur, Vcur,
-                nullptr, nullptr, nullptr,
-                kq_scale, il);
-            cb(cur, "attn_out", il);
-        }
-
-        ggml_tensor * ffn_inp = ggml_add(ctx0, cur, inpSA);
-        cb(ffn_inp, "ffn_inp", il);
-
-        cur = build_norm(ffn_inp, model.layers[il].ffn_norm, NULL, LLM_NORM_RMS, il);
-        cb(cur, "ffn_norm", il);
-
-        cur = build_ffn(cur,
-                ffn_up, NULL, NULL,
-                ffn_gate, NULL, NULL,
-                ffn_down, NULL, NULL,
-                NULL, LLM_FFN_SILU, LLM_FFN_PAR, il);
-
-        cur = ggml_add(ctx0, cur, ffn_inp);
-        cb(cur, "ffn_out", il);
-
-        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;
-
-    cur = build_lora_mm(model.output, cur);
-    cb(cur, "result_output", -1);
-    res->t_logits = cur;
-    ggml_build_forward_expand(gf, cur);
-}

data/ext/sources/examples/talk-llama/models/cohere2-iswa.cpp

@@ -1,134 +0,0 @@
-#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
-            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);
-}

data/ext/sources/examples/talk-llama/models/command-r.cpp

@@ -1,122 +0,0 @@
-#include "models.h"
-
-
-
-llm_build_command_r::llm_build_command_r(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();
-
-    ggml_tensor * inp_out_ids = build_inp_out_ids();
-
-    for (int il = 0; il < n_layer; ++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
-        {
-            // 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 (model.layers[il].attn_q_norm) {
-                Qcur = build_norm(Qcur, model.layers[il].attn_q_norm, NULL, LLM_NORM, il);
-                cb(Qcur, "Qcur", il);
-            }
-            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);
-
-            if (model.layers[il].attn_k_norm) {
-                Kcur = build_norm(Kcur, model.layers[il].attn_k_norm, NULL, LLM_NORM, il);
-                cb(Kcur, "Kcur", il);
-            }
-            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,
-                    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);
-}

data/ext/sources/examples/talk-llama/models/dbrx.cpp

@@ -1,123 +0,0 @@
-#include "models.h"
-
-
-llm_build_dbrx::llm_build_dbrx(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_ASSERT(n_embd_head == hparams.n_rot);
-
-    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;
-
-        // norm
-        cur = build_norm(inpL,
-                model.layers[il].attn_norm, NULL,
-                LLM_NORM, il);
-        cb(cur, "attn_norm", il);
-
-        // self-attention
-        {
-            ggml_tensor * Qcur = nullptr;
-            ggml_tensor * Kcur = nullptr;
-            ggml_tensor * Vcur = nullptr;
-
-            cur = build_lora_mm(model.layers[il].wqkv, cur);
-            cb(cur, "wqkv", il);
-
-            cur = ggml_clamp(ctx0, cur, -hparams.f_clamp_kqv, hparams.f_clamp_kqv);
-            cb(cur, "wqkv_clamped", 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);
-        }
-
-        ggml_tensor * ffn_inp = ggml_add(ctx0, cur, inpSA);
-        cb(ffn_inp, "ffn_inp", il);
-
-        // feed-forward network
-        // MoE branch
-        cur = build_norm(ffn_inp,
-                model.layers[il].attn_out_norm, NULL,
-                LLM_NORM, il);
-        cb(cur, "attn_out_norm", il);
-
-        cur = build_moe_ffn(cur,
-                model.layers[il].ffn_gate_inp,
-                model.layers[il].ffn_up_exps,
-                model.layers[il].ffn_gate_exps,
-                model.layers[il].ffn_down_exps,
-                nullptr,
-                n_expert, n_expert_used,
-                LLM_FFN_SILU, true,
-                false, 0.0,
-                LLAMA_EXPERT_GATING_FUNC_TYPE_SOFTMAX,
-                il);
-        cb(cur, "ffn_moe_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, -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);
-}

data/ext/sources/examples/talk-llama/models/deci.cpp

@@ -1,135 +0,0 @@
-#include "models.h"
-
-
-
-llm_build_deci::llm_build_deci(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);
-
-    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();
-
-    const float kq_scale =
-        hparams.f_attention_scale == 0.0f ? 1.0f / sqrtf(float(n_embd_head)) : hparams.f_attention_scale;
-
-    ggml_tensor * inp_out_ids = build_inp_out_ids();
-
-    for (int il = 0; il < n_layer; ++il) {
-        ggml_tensor * inpSA     = inpL;
-        const int64_t n_head_kv = hparams.n_head_kv(il);
-        const int64_t n_head    = hparams.n_head(il);
-        const int64_t n_ff      = hparams.n_ff(il);
-
-        if (n_head == 0) {
-            // attention-free layer of Llama-3_1-Nemotron-51B
-            cur = inpL;
-        } else {
-            // norm
-            cur = build_norm(inpL, model.layers[il].attn_norm, NULL, LLM_NORM_RMS, il);
-            cb(cur, "attn_norm", il);
-        }
-        if (n_head > 0 && n_head_kv == 0) {
-            // "linear attention" of Llama-3_1-Nemotron-51B
-            cur = build_lora_mm(model.layers[il].wo, cur);
-            cb(cur, "wo", il);
-        } else if (n_head > 0) {
-            // 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);
-        }
-        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);
-        }
-        // FFN-free layer of Llama-3_1-Nemotron-Ultra-253B
-        if (n_ff == 0) {
-            continue;
-        }
-        // modified to support attention-free layer of Llama-3_1-Nemotron-51B
-        ggml_tensor * ffn_inp = cur;
-        if (n_head > 0) {
-            ffn_inp = ggml_add(ctx0, cur, inpSA);
-            cb(ffn_inp, "ffn_inp", il);
-        }
-        // feed-forward network
-        if (model.layers[il].ffn_gate_inp == nullptr) {
-            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);
-}