From ab3e63ca1276761b123ddaf6e7ac49d273e48a99 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jukka=20Sepp=C3=A4nen?=
 <40791699+kijai@users.noreply.github.com>
Date: Mon, 17 Jun 2024 19:50:23 +0300
Subject: [PATCH] Update README.md

---
 README.md | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 90f40f2..ec853bf 100644
--- a/README.md
+++ b/README.md
@@ -1,6 +1,6 @@
 # WORK IN PROGRESS
 
-## Currently requires `flash_attn` !
+## Note: Sampling is slow without `flash_attn` !
 
 For Linux users this doesn't mean anything but `pip install flash_attn`. 
 
@@ -8,6 +8,8 @@ However doing same on Windows currently will most likely fail if you do not have
 Alternative for Windows can be pre-built wheels from here, has to match your python environment:
 https://github.com/bdashore3/flash-attention/releases
 
+If flash_attn is not installed, attention code will fallback to torch SDP attention, which is at least twice as slow and memory hungry.
+
 ## Text encoder setup
 
 Lumina-next uses Google's Gemma-2b -LLM: https://huggingface.co/google/gemma-2b