diff --git a/python/sglang/srt/layers/attention/wave_backend.py b/python/sglang/srt/layers/attention/wave_backend.py
index 18c193ade493..2e01c554ce92 100644
--- a/python/sglang/srt/layers/attention/wave_backend.py
+++ b/python/sglang/srt/layers/attention/wave_backend.py
@@ -7,7 +7,7 @@
 import triton
 import triton.language as tl
 
-from sglang.srt.layers.attention import AttentionBackend
+from sglang.srt.layers.attention.base_attn_backend import AttentionBackend
 from sglang.srt.layers.attention.utils import create_flashinfer_kv_indices_triton
 from sglang.srt.layers.dp_attention import get_attention_tp_size
 from sglang.srt.model_executor.forward_batch_info import ForwardBatch, ForwardMode
@@ -88,7 +88,7 @@ class WaveAttnBackend(AttentionBackend):
     def __init__(
         self,
         model_runner: ModelRunner,
-        skip_prefill: bool,
+        skip_prefill: bool = False,
         kv_indptr_buf: Optional[torch.Tensor] = None,
     ):
         # Lazy import to avoid the initialization of cuda context
diff --git a/python/sglang/srt/layers/quantization/fp8.py b/python/sglang/srt/layers/quantization/fp8.py
index 7e668fb956ef..31b6d09dec23 100644
--- a/python/sglang/srt/layers/quantization/fp8.py
+++ b/python/sglang/srt/layers/quantization/fp8.py
@@ -860,7 +860,7 @@ def process_weights_hip_int4(self, layer: Module):
             layer.w13_weight_scale1[expert_id] *= max_w13_scales[expert_id]
             layer.w2_weight_scale1[expert_id] *= layer.w2_weight_scale[expert_id]
 
-    def process_weights_hip_scale_padding(self, layer: Module, padding_size: int):
+    def process_weights_hip_scale_padding(self, layer: Module, padding_size: int=0):
         from sglang.srt.layers.moe.fused_moe_triton.fused_moe import (
             padding_size,  # Avoid circular import
         )