diff --git a/vllm_omni/diffusion/diffusion_engine.py b/vllm_omni/diffusion/diffusion_engine.py
index 9a5e395ae..2bc3074b5 100644
--- a/vllm_omni/diffusion/diffusion_engine.py
+++ b/vllm_omni/diffusion/diffusion_engine.py
@@ -4,7 +4,7 @@
 import multiprocessing as mp
 import time
 import weakref
-from collections.abc import Callable
+from collections.abc import Callable, Iterable
 from dataclasses import dataclass
 from typing import Any
 
@@ -361,3 +361,8 @@ class DiffusionEngine:
 
     def close(self) -> None:
         self._finalizer()
+
+    def abort(self, request_id: str | Iterable[str]) -> None:
+        # TODO implement it
+        logger.warning("DiffusionEngine abort is not implemented yet")
+        pass
diff --git a/vllm_omni/entrypoints/async_omni_diffusion.py b/vllm_omni/entrypoints/async_omni_diffusion.py
index 0a4976a37..1a7f1174c 100644
--- a/vllm_omni/entrypoints/async_omni_diffusion.py
+++ b/vllm_omni/entrypoints/async_omni_diffusion.py
@@ -10,7 +10,7 @@ enabling concurrent request handling and streaming generation.
 
 import asyncio
 import uuid
-from collections.abc import AsyncGenerator
+from collections.abc import AsyncGenerator, Iterable
 from concurrent.futures import ThreadPoolExecutor
 from dataclasses import fields
 from typing import Any
@@ -263,6 +263,10 @@ class AsyncOmniDiffusion:
         except Exception:
             pass
 
+    async def abort(self, request_id: str | Iterable[str]) -> None:
+        """Abort a request."""
+        self.engine.abort(request_id)
+
     @property
     def is_running(self) -> bool:
         """Check if the engine is running."""