From 1e41a53770e4082e21e46fd7b4c4799b915651c4 Mon Sep 17 00:00:00 2001
From: OlivierDehaene <23298448+OlivierDehaene@users.noreply.github.com>
Date: Wed, 19 Apr 2023 12:52:24 +0200
Subject: [PATCH] explicit

---
 server/text_generation_server/models/__init__.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/server/text_generation_server/models/__init__.py b/server/text_generation_server/models/__init__.py
index 6b015a4a..b0f87047 100644
--- a/server/text_generation_server/models/__init__.py
+++ b/server/text_generation_server/models/__init__.py
@@ -33,7 +33,7 @@ try:
         supported = is_sm75 or is_sm8x or is_sm90
         if not supported:
             raise ImportError(f"GPU with CUDA capability {major} {minor} is not supported")
-        FLASH_ATTENTION = supported
+        FLASH_ATTENTION = True
     else:
         FLASH_ATTENTION = False
 except ImportError: