From ac3b8869538c7fbdb48ff141d78c4dea091789f0 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Johannes=20G=C3=A4=C3=9Fler?= <johannesg@5d6.de>
Date: Fri, 16 Jun 2023 20:25:51 +0200
Subject: llama : fix embd when offloading non-repeating layers (#1891)

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

diff --git a/llama.cpp b/llama.cpp
index a904388..81f047e 100644
--- a/llama.cpp
+++ b/llama.cpp
@@ -1658,7 +1658,7 @@ static bool llama_eval_internal(
 
         // cur = cur*norm(broadcasted)
         cur = ggml_mul(ctx0, cur, model.norm);
-        offload_func_nr(cur);
+        // offload_func_nr(cur); // TODO CPU + GPU mirrored backend
         ggml_set_name(cur, "result_norm");
 
         embeddings = cur;
-- 
cgit v1.2.3