diff --git a/server/Makefile-flash-att-v2 b/server/Makefile-flash-att-v2
index a7d633563d8..34fd1e33073 100644
--- a/server/Makefile-flash-att-v2
+++ b/server/Makefile-flash-att-v2
@@ -1,4 +1,4 @@
-flash_att_v2_commit := 4f285b354796fb17df8636485b9a04df3ebbb7dc
+flash_att_v2_commit := 92dd5703ecdb99aa4a4aee9817f28557907403a2 # v2.3.6
 
 flash-attention-v2:
     # Clone flash attention
@@ -10,4 +10,4 @@ build-flash-attention-v2: flash-attention-v2
 	cd flash-attention-v2 && python setup.py build
 
 install-flash-attention-v2: build-flash-attention-v2
-	cd flash-attention-v2 && python setup.py install
\ No newline at end of file
+	cd flash-attention-v2 && python setup.py install
diff --git a/server/text_generation_server/utils/flash_attn.py b/server/text_generation_server/utils/flash_attn.py
index c472d1fceab..f7d4bcc7d30 100644
--- a/server/text_generation_server/utils/flash_attn.py
+++ b/server/text_generation_server/utils/flash_attn.py
@@ -66,12 +66,15 @@ def attention(
             out,
             cu_seqlens,
             cu_seqlens,
+            None, # seqused_k added in ce3e728
             max_s,
             max_s,
             0.0,
             softmax_scale,
             False,
             True,
+            -1, # window_size[0] added in 083e8f52. -1 means infinite window size
+            -1, # window_size[1] added in 083e8f52. -1 means infinite window size
             False,
             None,
         )