Merge branch 'ggml-org:master' into master

Author: Thireus

src/llama-model.cpp

@@ -675,10 +675,17 @@ void llama_model::load_hparams(llama_model_loader & ml) {
             } break;
         case LLM_ARCH_MINICPM:
             {
+                // Backward-compatible defaults for older MiniCPM GGUFs
+                hparams.f_embedding_scale = 12.0f;
+                hparams.f_residual_scale  = 1.4f / sqrtf(float(hparams.n_layer));
+                hparams.f_logit_scale     = hparams.n_embd ? (256.0f / float(hparams.n_embd)) : 1.0f;
+
                 ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps);
-                ml.get_key(LLM_KV_EMBEDDING_SCALE,             hparams.f_embedding_scale);
-                ml.get_key(LLM_KV_RESIDUAL_SCALE,              hparams.f_residual_scale);
-                ml.get_key(LLM_KV_LOGIT_SCALE,                 hparams.f_logit_scale);
+
+                // Optional KV reads, override defaults if present in newer GGUF exports
+                ml.get_key(LLM_KV_EMBEDDING_SCALE, hparams.f_embedding_scale, /*required=*/false);
+                ml.get_key(LLM_KV_RESIDUAL_SCALE, hparams.f_residual_scale, /*required=*/false);
+                ml.get_key(LLM_KV_LOGIT_SCALE, hparams.f_logit_scale, /*required=*/false);
 
                 // MiniCPM uses rope by default, unlike Granite which uses it as a switch
                 hparams.rope_finetuned = true;