From 1170a957324e13c6a908458fab5de1012f0306ba Mon Sep 17 00:00:00 2001 From: JohannesGaessler Date: Fri, 16 Jun 2023 15:34:46 +0200 Subject: [PATCH] Fixed embd when offloading non-repeating layers --- llama.cpp | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/llama.cpp b/llama.cpp index b8bc0d821..ecee56452 100644 --- a/llama.cpp +++ b/llama.cpp @@ -1654,7 +1654,7 @@ 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;