diff --git a/vllm/attention/ops/triton_flash_attention.py b/vllm/attention/ops/triton_flash_attention.py
index 1741091e0958e..3d53cd4b5700f 100644
--- a/vllm/attention/ops/triton_flash_attention.py
+++ b/vllm/attention/ops/triton_flash_attention.py
@@ -367,12 +367,12 @@ def attn_fwd(
     IS_CAUSAL: tl.constexpr,
     BLOCK_M: tl.constexpr,
     BLOCK_DMODEL: tl.constexpr,
+    USE_FP8: tl.constexpr,
     BLOCK_N: tl.constexpr,
     PRE_LOAD_V: tl.constexpr,
     BIAS_TYPE: tl.constexpr,
     ENABLE_DROPOUT: tl.constexpr,
     RETURN_ENCODED_SOFTMAX: tl.constexpr,
-    USE_FP8: tl.constexpr,
 ):
     start_m = tl.program_id(0)
     off_h_q = tl.program_id(1)