From e3bc7c7a2451a3acc75a37c286c5dab51deafcaa Mon Sep 17 00:00:00 2001
From: Slaren <2141330+slaren@users.noreply.github.com>
Date: Fri, 28 Apr 2023 00:48:01 +0200
Subject: [PATCH] cuBLAS: also pin kv cache

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

diff --git a/llama.cpp b/llama.cpp
index 8c89e9912e9faf..bd065e961adecc 100644
--- a/llama.cpp
+++ b/llama.cpp
@@ -136,7 +136,7 @@ struct llama_kv_cache {
 
     struct ggml_context * ctx = NULL;
 
-    llama_buffer buf;
+    llama_ctx_buffer buf;
 
     int n; // number of tokens currently in the cache