From f233f8ad8ff461f188fef9bd8e44f212bd5bb38a Mon Sep 17 00:00:00 2001
From: Mikko Juola <mikjuo@gmail.com>
Date: Sat, 18 Mar 2023 01:34:40 -0700
Subject: [PATCH] Forgot to mark last benchmark at March 17

---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 3262f86..f0dddaa 100644
--- a/README.md
+++ b/README.md
@@ -177,7 +177,7 @@ LLaMA-13B: AMD Ryzen 3950X + OpenCL GTX 3090 Ti:  <ran out of GPU memory>
 LLaMA-13B: AMD Ryzen 3950X + OpenCL Ryzen 3950X:  1232ms / token
 LLaMA-30B: AMD Ryzen 5950X + OpenCL Ryzen 5950X:  4098ms / token
 
-# commit 3d0afcf24309f28ec540ed7645c35400a865ad6f
+# commit 3d0afcf24309f28ec540ed7645c35400a865ad6f  (17 March 2023)
 # I've been focusing on making the ordinary non-OpenCL CPU implementation
 # faster and I got some gains, most importantly from multithreading.
 # There is Float16 support now, so I've added f16/f32 to these tables: