talk-llama : sync llama.cpp

examples/talk-llama/models/rnd1.cpp

@@ -1,7 +1,67 @@
 #include "models.h"
 
+void llama_model_rnd1::load_arch_hparams(llama_model_loader & ml) {
+    ml.get_key(LLM_KV_EXPERT_FEED_FORWARD_LENGTH, hparams.n_ff_exp, false);
+
+    ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps);
+    switch (hparams.n_layer) {
+        case 48: type = LLM_TYPE_30B_A3B; break;
+        default: type = LLM_TYPE_UNKNOWN;
+    }
+    // Set non-causal attention for diffusion models
+    hparams.causal_attn = false;
+}
+
+void llama_model_rnd1::load_arch_tensors(llama_model_loader &) {
+    LLAMA_LOAD_LOCALS;
+
+    tok_embd = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, 0);
+
+    // output
+    output_norm = create_tensor(tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}, 0);
+    output      = create_tensor(tn(LLM_TENSOR_OUTPUT,      "weight"), {n_embd, n_vocab}, TENSOR_NOT_REQUIRED);
+    // if output is NULL, init from the input tok embed
+    if (output == NULL) {
+        output = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, TENSOR_DUPLICATED);
+    }
+
+    for (int i = 0; i < n_layer; ++i) {
+        auto & layer = layers[i];
+
+        layer.attn_norm = create_tensor(tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}, 0);
+
+        create_tensor_qkv(layer, i, n_embd, n_embd_head_k * n_head, n_embd_gqa, n_embd_gqa, 0);
+        layer.wo = create_tensor(tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd_head_k * n_head, n_embd}, 0);
+
+        layer.attn_k_norm = create_tensor(tn(LLM_TENSOR_ATTN_K_NORM, "weight", i), {n_embd_head_k}, 0);
+        layer.attn_q_norm = create_tensor(tn(LLM_TENSOR_ATTN_Q_NORM, "weight", i), {n_embd_head_k}, 0);
+
+        layer.ffn_norm = create_tensor(tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}, 0);
+
+        layer.ffn_gate_inp = create_tensor(tn(LLM_TENSOR_FFN_GATE_INP, "weight", i), {n_embd, n_expert}, 0);
+
+        if (n_expert == 0) {
+            throw std::runtime_error("n_expert must be > 0 for QWEN3MOE");
+        }
+        if (n_expert_used == 0) {
+            throw std::runtime_error("n_expert_used must be > 0 for QWEN3MOE");
+        }
+
+        // MoE branch
+        const int64_t n_ff_exp = hparams.n_ff_exp ? hparams.n_ff_exp : n_ff / n_expert_used;
+
+        layer.ffn_gate_exps = create_tensor(tn(LLM_TENSOR_FFN_GATE_EXPS, "weight", i), {  n_embd, n_ff_exp, n_expert}, 0);
+        layer.ffn_down_exps = create_tensor(tn(LLM_TENSOR_FFN_DOWN_EXPS, "weight", i), {n_ff_exp,   n_embd, n_expert}, 0);
+        layer.ffn_up_exps   = create_tensor(tn(LLM_TENSOR_FFN_UP_EXPS,   "weight", i), {  n_embd, n_ff_exp, n_expert}, 0);
+    }
+}
+
+std::unique_ptr<llm_graph_context> llama_model_rnd1::build_arch_graph(const llm_graph_params & params) const {
+    return std::make_unique<graph>(*this, params);
+}
+
 // RND1 is a Qwen3Moe AR model converted to diffusion model.
-llm_build_rnd1::llm_build_rnd1(const llama_model & model, const llm_graph_params & params) : llm_graph_context(params) {
+llama_model_rnd1::graph::graph(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());