Yet another post-merge dupe.

Author: pwilkin

src/llama-model.cpp

@@ -17404,150 +17404,6 @@ struct llm_build_bailingmoe2 : public llm_graph_context {
     }
 };
 
-struct llm_build_bailingmoe2 : public llm_graph_context {
-    llm_build_bailingmoe2(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_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();
-
-        const int n_transformer_layers = n_layer - hparams.nextn_predict_layers;
-        for (int il = 0; il < n_transformer_layers; ++il) {
-            ggml_tensor * inpSA = inpL;
-
-            // norm
-            cur = build_norm(inpL,
-                    model.layers[il].attn_norm, NULL,
-                    LLM_NORM_RMS, il);
-            cb(cur, "attn_norm", il);
-
-            // self_attention
-            {
-                cur = build_lora_mm(model.layers[il].wqkv, cur);
-                cb(cur, "wqkv", il);
-
-                ggml_tensor * 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));
-                ggml_tensor * 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));
-                ggml_tensor * 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 = build_norm(Qcur, model.layers[il].attn_q_norm, NULL, LLM_NORM_RMS, il);
-                cb(Qcur, "Qcur_normed", 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
-                        );
-
-                Kcur = build_norm(Kcur, model.layers[il].attn_k_norm, NULL, LLM_NORM_RMS, il);
-                cb(Kcur, "Kcur_normed", 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_transformer_layers - 1 && inp_out_ids) {
-                cur   = ggml_get_rows(ctx0,   cur, inp_out_ids);
-                inpSA = ggml_get_rows(ctx0, inpSA, inp_out_ids);
-            }
-
-            ggml_tensor * sa_out = ggml_add(ctx0, cur, inpSA);
-            cb(sa_out, "sa_out", il);
-
-            // MoE branch
-            cur = build_norm(sa_out,
-                    model.layers[il].ffn_norm, NULL,
-                    LLM_NORM_RMS, il);
-            cb(cur, "ffn_norm", il);
-
-            if (static_cast<uint32_t>(il) < hparams.n_layer_dense_lead) {
-                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);
-            } else {
-                ggml_tensor * moe_out =
-                    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,
-                            model.layers[il].ffn_exp_probs_b,
-                            n_expert, n_expert_used,
-                            LLM_FFN_SILU, hparams.expert_weights_norm,
-                            true, hparams.expert_weights_scale,
-                            (llama_expert_gating_func_type) hparams.expert_gating_func,
-                            il);
-                cb(moe_out, "ffn_moe_out", il);
-
-                {
-                    ggml_tensor * ffn_shexp = build_ffn(cur,
-                            model.layers[il].ffn_up_shexp,   NULL, NULL,
-                            model.layers[il].ffn_gate_shexp, NULL, NULL,
-                            model.layers[il].ffn_down_shexp, NULL, NULL,
-                            NULL,
-                            LLM_FFN_SILU, LLM_FFN_PAR, il);
-                    cb(ffn_shexp, "ffn_shexp", il);
-
-                    cur = ggml_add(ctx0, moe_out, ffn_shexp);
-                    cb(cur, "ffn_out", il);
-                }
-            }
-
-            cur = ggml_add(ctx0, cur, sa_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_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);
-    }
-};
-
 struct llm_build_dots1 : public llm_graph_context {
     llm_build_dots1(const llama_model & model, const llm_graph_params & params) : llm_graph_context(params) {
         const int64_t n_embd_head = hparams.n_embd_head_v;