diff --git a/lightx2v/models/networks/wan/infer/audio/transformer_infer.py b/lightx2v/models/networks/wan/infer/audio/transformer_infer.py
old mode 100755
new mode 100644
index 379f1e1fb..23c3cb983
--- a/lightx2v/models/networks/wan/infer/audio/transformer_infer.py
+++ b/lightx2v/models/networks/wan/infer/audio/transformer_infer.py
@@ -404,6 +404,7 @@ def infer_self_attn_with_kvcache(self, phase, grid_sizes, x, seq_lens, freqs, sh
                 attn_v = kv_cache.v_cache(self.block_idx, attn_start, local_end_idx)
                 if use_local_cache_rope:
                     attn_k = self._apply_rope_with_cache_range(
+                        phase,
                         attn_k,
                         freqs,
                         h,
@@ -432,6 +433,7 @@ def infer_self_attn_with_kvcache(self, phase, grid_sizes, x, seq_lens, freqs, sh
             rope_global_end = None if use_local_cache_rope else current_end
             rope_sink_tokens = 0 if use_local_cache_rope else sink_tokens
             q = self._apply_rope_with_cache_range(
+                phase,
                 q,
                 freqs,
                 h,
@@ -446,6 +448,7 @@ def infer_self_attn_with_kvcache(self, phase, grid_sizes, x, seq_lens, freqs, sh
                 sink_tokens=rope_sink_tokens,
             )
             attn_k = self._apply_rope_with_cache_range(
+                phase,
                 attn_k,
                 freqs,
                 h,