diff --git a/llm/llama.cpp b/llm/llama.cpp
index 952d03db..614d3b91 160000
--- a/llm/llama.cpp
+++ b/llm/llama.cpp
@@ -1 +1 @@
-Subproject commit 952d03dbead16e4dbdd1d3458486340673cc2465
+Subproject commit 614d3b914e1c3e02596f869649eb4f1d3b68614d
diff --git a/llm/patches/05-clip-fix.diff b/llm/patches/05-clip-fix.diff
deleted file mode 100644
index 3f68a5bb..00000000
--- a/llm/patches/05-clip-fix.diff
+++ /dev/null
@@ -1,24 +0,0 @@
-diff --git a/examples/llava/clip.cpp b/examples/llava/clip.cpp
-index e3c9bcd4..b43f892d 100644
---- a/examples/llava/clip.cpp
-+++ b/examples/llava/clip.cpp
-@@ -573,14 +573,16 @@ static ggml_cgraph * clip_image_build_graph(clip_ctx * ctx, const clip_image_f32
-     struct ggml_tensor * embeddings = inp;
-     if (ctx->has_class_embedding) {
-         embeddings = ggml_new_tensor_3d(ctx0, GGML_TYPE_F32, hidden_size, num_positions, batch_size);
-+    }
-+    ggml_set_name(embeddings, "embeddings");
-+    ggml_set_input(embeddings);
-+
-+    if (ctx->has_class_embedding) {
-         embeddings = ggml_acc(ctx0, embeddings, model.class_embedding,
-                 embeddings->nb[1], embeddings->nb[2], embeddings->nb[3], 0);
-         embeddings = ggml_acc(ctx0, embeddings, inp,
-                 embeddings->nb[1], embeddings->nb[2], embeddings->nb[3], model.class_embedding->nb[1]);
-     }
--    ggml_set_name(embeddings, "embeddings");
--    ggml_set_input(embeddings);
--
- 
-     struct ggml_tensor * positions = ggml_new_tensor_1d(ctx0, GGML_TYPE_I32, num_positions);
-     ggml_set_name(positions, "positions");