[diffusion] refactor: refactor and simplify teacache for cachabledit and wanvideo (#16396)

Co-authored-by: Brain97 <Brain97@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Mick <mickjagger19@icloud.com>
Co-authored-by: blahblah <blahblah>

python/sglang/multimodal_gen/test/server/testcase_configs.py

@@ -191,6 +191,9 @@ class DiffusionSamplingParams:
 
     num_outputs_per_prompt: int = 1
 
+    # TeaCache acceleration
+    enable_teacache: bool = False
+
 
 @dataclass(frozen=True)
 class DiffusionTestCase:
@@ -457,6 +460,20 @@ ONE_GPU_CASES_B: list[DiffusionTestCase] = [
             prompt=T2V_PROMPT,
         ),
     ),
+    # TeaCache acceleration test for Wan video model
+    DiffusionTestCase(
+        "wan2_1_t2v_1.3b_teacache_enabled",
+        DiffusionServerArgs(
+            model_path="Wan-AI/Wan2.1-T2V-1.3B-Diffusers",
+            modality="video",
+            warmup=0,
+            custom_validator="video",
+        ),
+        DiffusionSamplingParams(
+            prompt=T2V_PROMPT,
+            enable_teacache=True,
+        ),
+    ),
     # LoRA test case for single transformer + merge/unmerge API test
     # Note: Uses dynamic_lora_path instead of lora_path to test LayerwiseOffload + set_lora interaction
     # Server starts WITHOUT LoRA, then set_lora is called after startup (Wan models auto-enable layerwise offload)