diff --git a/python/sglang/multimodal_gen/configs/models/dits/mova_audio.py b/python/sglang/multimodal_gen/configs/models/dits/mova_audio.py
index 324d6b5e1..1240d5f44 100644
--- a/python/sglang/multimodal_gen/configs/models/dits/mova_audio.py
+++ b/python/sglang/multimodal_gen/configs/models/dits/mova_audio.py
@@ -45,7 +45,7 @@ class MOVAAudioArchConfig(DiTArchConfig):
     has_ref_conv: bool = False
     add_control_adapter: bool = False
     in_dim_control_adapter: int = 24
-    seperated_timestep: bool = False
+    separated_timestep: bool = False
     require_vae_embedding: bool = False
     require_clip_embedding: bool = False
     fuse_vae_embedding_in_latents: bool = False
diff --git a/python/sglang/multimodal_gen/configs/models/dits/mova_video.py b/python/sglang/multimodal_gen/configs/models/dits/mova_video.py
index a7983a45a..66156be4f 100644
--- a/python/sglang/multimodal_gen/configs/models/dits/mova_video.py
+++ b/python/sglang/multimodal_gen/configs/models/dits/mova_video.py
@@ -45,7 +45,7 @@ class MOVAVideoArchConfig(DiTArchConfig):
     has_ref_conv: bool = False
     add_control_adapter: bool = False
     in_dim_control_adapter: int = 24
-    seperated_timestep: bool = False
+    separated_timestep: bool = False
     require_vae_embedding: bool = True
     require_clip_embedding: bool = True
     fuse_vae_embedding_in_latents: bool = False
diff --git a/python/sglang/multimodal_gen/runtime/models/dits/mova_audio_dit.py b/python/sglang/multimodal_gen/runtime/models/dits/mova_audio_dit.py
index 2604c0ed2..f3deaf649 100644
--- a/python/sglang/multimodal_gen/runtime/models/dits/mova_audio_dit.py
+++ b/python/sglang/multimodal_gen/runtime/models/dits/mova_audio_dit.py
@@ -130,7 +130,7 @@ class WanAudioModel(CachableDiT, OffloadableDiTMixin):
         num_layers = config.num_layers
         has_image_pos_emb = config.has_image_pos_emb
         has_ref_conv = config.has_ref_conv
-        seperated_timestep = config.seperated_timestep
+        separated_timestep = config.separated_timestep
         require_vae_embedding = config.require_vae_embedding
         require_clip_embedding = config.require_clip_embedding
         fuse_vae_embedding_in_latents = config.fuse_vae_embedding_in_latents
@@ -139,7 +139,7 @@ class WanAudioModel(CachableDiT, OffloadableDiTMixin):
         self.dim = dim
         self.freq_dim = freq_dim
         self.patch_size = patch_size
-        self.seperated_timestep = seperated_timestep
+        self.separated_timestep = separated_timestep
         self.require_vae_embedding = require_vae_embedding
         self.require_clip_embedding = require_clip_embedding
         self.fuse_vae_embedding_in_latents = fuse_vae_embedding_in_latents
diff --git a/python/sglang/multimodal_gen/runtime/models/dits/mova_video_dit.py b/python/sglang/multimodal_gen/runtime/models/dits/mova_video_dit.py
index 76a5267f0..21de5b9b3 100644
--- a/python/sglang/multimodal_gen/runtime/models/dits/mova_video_dit.py
+++ b/python/sglang/multimodal_gen/runtime/models/dits/mova_video_dit.py
@@ -447,7 +447,7 @@ class WanModel(CachableDiT, OffloadableDiTMixin):
         num_layers = config.num_layers
         has_image_pos_emb = config.has_image_pos_emb
         has_ref_conv = config.has_ref_conv
-        seperated_timestep = config.seperated_timestep
+        separated_timestep = config.separated_timestep
         require_vae_embedding = config.require_vae_embedding
         require_clip_embedding = config.require_clip_embedding
         fuse_vae_embedding_in_latents = config.fuse_vae_embedding_in_latents
@@ -455,7 +455,7 @@ class WanModel(CachableDiT, OffloadableDiTMixin):
         self.dim = dim
         self.freq_dim = freq_dim
         self.patch_size = patch_size
-        self.seperated_timestep = seperated_timestep
+        self.separated_timestep = separated_timestep
         self.require_vae_embedding = require_vae_embedding
         self.require_clip_embedding = require_clip_embedding
         self.fuse_vae_embedding_in_latents = fuse_vae_embedding_in_latents