diff --git a/server/text_generation_server/utils/flash_attn.py b/server/text_generation_server/utils/flash_attn.py
index 1b59fbc5..02f01e65 100644
--- a/server/text_generation_server/utils/flash_attn.py
+++ b/server/text_generation_server/utils/flash_attn.py
@@ -72,7 +72,7 @@ def attention(
     softmax_scale,
     window_size_left=-1,
 ):
-    if window_size_left == 0:
+    if window_size_left <= 0 and window_size_left != -1:
         raise ValueError("`window_size_left` must be > 0 or -1")
 
     if HAS_FLASH_ATTN_V2_CUDA: