From 3ef747808a075039806d6a973abc44a09dce0935 Mon Sep 17 00:00:00 2001
From: Stephan Walter <stephan@walter.name>
Date: Sat, 1 Apr 2023 17:00:01 +0200
Subject: [PATCH] Be nice to CI machines by not allocating buffers

...for vocab_only=true
---
 llama.cpp | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/llama.cpp b/llama.cpp
index bed24207d..1b3157cd2 100644
--- a/llama.cpp
+++ b/llama.cpp
@@ -1608,7 +1608,7 @@ struct llama_context * llama_init_from_file(
     }
 
     // reserve memory for context buffers
-    {
+    if (!params.vocab_only) {
         if (!kv_cache_init(ctx->model.hparams, ctx->model.kv_self, memory_type, ctx->model.hparams.n_ctx)) {
             fprintf(stderr, "%s: kv_cache_init() failed for self-attention cache\n", __func__);
             llama_free(ctx);