From 16b9cd193965769089881bb8ec012fccca7b37b6 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Johannes=20G=C3=A4=C3=9Fler?= <johannesg@5d6.de>
Date: Mon, 19 Jun 2023 10:23:56 +0200
Subject: Convert vector to f16 for dequantize mul mat vec (#1913)

* Convert vector to f16 for dmmv

* compile option

* Added compilation option description to README

* Changed cmake CUDA_ARCHITECTURES from "OFF" to "native"
---
 llama.cpp | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'llama.cpp')

diff --git a/llama.cpp b/llama.cpp
index 2105e327..5401db00 100644
--- a/llama.cpp
+++ b/llama.cpp
@@ -1620,7 +1620,7 @@ static bool llama_eval_internal(
                     model.layers[il].w1,
                     cur);
             offload_func(cur);
-            ggml_set_name(cur, "result_w2");
+            ggml_set_name(cur, "result_w1");
 
             // SILU activation
             cur = ggml_silu(ctx0, cur);
-- 
cgit v1.2.3