From b784ed73cf89cc1c820d18a4bf6f232f91004b47 Mon Sep 17 00:00:00 2001
From: Tri Dao <tridpq@gmail.com>
Date: Fri, 25 Nov 2022 10:49:17 -0800
Subject: [PATCH] [Docs] Clarify OpenFold speedup

---
 usage.md | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/usage.md b/usage.md
index f2688cc..b34e34c 100644
--- a/usage.md
+++ b/usage.md
@@ -89,7 +89,8 @@ yields the fastest BERT training on cloud instances in MLPerf training 2.0 (June
   memory-efficient, and GPU-friendly PyTorch reproduction of AlphaFold 2. With
   FlashAttention as one of its
   [components](https://twitter.com/gahdritz/status/1595420944880779266), it is
-  up to 3x faster than AlphaFold2, and can predict 2x longer structures.
+  up to 3x faster than AlphaFold2 to run inference on short sequences, and can
+  predict 2x longer structures.
 
 ## Different implementations