cuBLAS: also pin kv cache

ggml-org · Apr 27, 2023 · e3bc7c7 · e3bc7c7
1 parent 7455432
commit e3bc7c7
Showing 1 changed file with 1 addition and 1 deletion.
diff --git 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