From b9280718b5c84074dcad768cc697e5388b5b4821 Mon Sep 17 00:00:00 2001
From: Concedo <39025047+LostRuins@users.noreply.github.com>
Date: Sun, 21 Sep 2025 08:38:37 +0800
Subject: [PATCH] fix bge memory excessive usage?

---
 src/llama-context.cpp | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/llama-context.cpp b/src/llama-context.cpp
index 17479166c..a293526b4 100644
--- a/src/llama-context.cpp
+++ b/src/llama-context.cpp
@@ -270,7 +270,7 @@ llama_context::llama_context(
         }
     }
 
-    if (!hparams.vocab_only) {
+    if (!hparams.vocab_only && memory) {
         llama_memory_context_ptr mctx;
         if (memory) {
             LLAMA_LOG_DEBUG("%s: reserving full memory module\n", __func__);