[diffusion] model: support TurboWan2.1-T2V-1.3B/14B SLA (#15888)

python/sglang/multimodal_gen/configs/models/dits/wanvideo.py

@@ -30,6 +30,7 @@ class WanVideoArchConfig(DiTArchConfig):
             r"^blocks\.(\d+)\.attn1\.to_out\.0\.(.*)$": r"blocks.\1.to_out.\2",
             r"^blocks\.(\d+)\.attn1\.norm_q\.(.*)$": r"blocks.\1.norm_q.\2",
             r"^blocks\.(\d+)\.attn1\.norm_k\.(.*)$": r"blocks.\1.norm_k.\2",
+            r"^blocks\.(\d+)\.attn1\.attn_op\.local_attn\.proj_l\.(.*)$": r"blocks.\1.attn1.local_attn.proj_l.\2",
             r"^blocks\.(\d+)\.attn2\.to_out\.0\.(.*)$": r"blocks.\1.attn2.to_out.\2",
             r"^blocks\.(\d+)\.ffn\.net\.0\.proj\.(.*)$": r"blocks.\1.ffn.fc_in.\2",
             r"^blocks\.(\d+)\.ffn\.net\.2\.(.*)$": r"blocks.\1.ffn.fc_out.\2",
@@ -87,6 +88,8 @@ class WanVideoArchConfig(DiTArchConfig):
     )
     num_frames_per_block: int = 3
     sliding_window_num_frames: int = 21
+    attention_type: str = "original"
+    sla_topk: float = 0.1
 
     def __post_init__(self):
         super().__post_init__()

python/sglang/multimodal_gen/configs/pipeline_configs/wan.py

@@ -92,6 +92,16 @@ class WanT2V480PConfig(PipelineConfig):
         self.vae_config.load_decoder = True
 
 
+@dataclass
+class TurboWanT2V480PConfig(WanT2V480PConfig):
+    """Base configuration for Wan T2V 1.3B pipeline architecture."""
+
+    flow_shift: float | None = 8.0
+    dmd_denoising_steps: list[int] | None = field(
+        default_factory=lambda: [988, 932, 852, 608]
+    )
+
+
 @dataclass
 class WanT2V720PConfig(WanT2V480PConfig):
     """Base configuration for Wan T2V 14B 720P pipeline architecture."""