From 86f5623d904cfd392fdeb14a143097b4074660f6 Mon Sep 17 00:00:00 2001
From: yummy <57988893+jk3456a@users.noreply.github.com>
Date: Thu, 24 Jul 2025 17:50:51 +0800
Subject: [PATCH] llama : fix MiniCPM inference after Granite Four changes
 (#14850)

MiniCPM models use the llm_build_granite constructor which was changed
in the Granite Four PR to use hparams.rope_finetuned instead of a
use_rope parameter. MiniCPM models need rope enabled by default.

Fixes inference from gibberish to correct responses.
---
 src/llama-model.cpp | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/src/llama-model.cpp b/src/llama-model.cpp
index 35e718aa98..a997a1e80f 100644
--- a/src/llama-model.cpp
+++ b/src/llama-model.cpp
@@ -646,6 +646,9 @@ void llama_model::load_hparams(llama_model_loader & ml) {
                 ml.get_key(LLM_KV_RESIDUAL_SCALE,              hparams.f_residual_scale);
                 ml.get_key(LLM_KV_LOGIT_SCALE,                 hparams.f_logit_scale);
 
+                // MiniCPM uses rope by default, unlike Granite which uses it as a switch
+                hparams.rope_finetuned = true;
+
                 switch (hparams.n_layer) {
                     case 52: type = LLM_TYPE_1B; break;
                     case 40: type = LLM_TYPE_2B; break;