src: reduce the logging

Author: kpouget

src/llama-kv-cache.cpp

@@ -86,8 +86,10 @@ bool llama_kv_cache_unified::init(
             buft = ggml_backend_cpu_buffer_type();
         }
 
+	/*
         LLAMA_LOG_DEBUG("%s: layer %3d: n_embd_k_gqa = %d, n_embd_v_gqa = %d, dev = %s\n", __func__,
                 i, n_embd_k_gqa, n_embd_v_gqa, dev_name);
+	*/
 
         ggml_context * ctx = ctx_for_buft(buft);
         if (!ctx) {

src/llama-model-loader.cpp

@@ -668,7 +668,7 @@ llama_model_loader::llama_model_loader(
             }
             replace_all(value, "\n", "\\n");
 
-            LLAMA_LOG_INFO("%s: - kv %3d: %42s %-16s = %s\n", __func__, i, name, type_name.c_str(), value.c_str());
+            //LLAMA_LOG_INFO("%s: - kv %3d: %42s %-16s = %s\n", __func__, i, name, type_name.c_str(), value.c_str());
         }
 
         // print type counts

src/llama-vocab.cpp

@@ -1974,8 +1974,8 @@ void llama_vocab::impl::load(llama_model_loader & ml, const LLM_KV & kv) {
             } else {
                 // token is control, but not marked as EOG -> print a debug log
                 if (id_to_token[t.second].attr & LLAMA_TOKEN_ATTR_CONTROL && special_eog_ids.count(t.second) == 0) {
-                    LLAMA_LOG_DEBUG("%s: control token: %6d '%s' is not marked as EOG\n",
-                            __func__, t.second, t.first.c_str());
+                    //LLAMA_LOG_DEBUG("%s: control token: %6d '%s' is not marked as EOG\n",
+                    //        __func__, t.second, t.first.c_str());
                 }
             }
         }