[Core] Support reset_prefix_cache (#12284)

2025-01-22 10:52:27 -08:00
parent 96f6a7596f
commit 7206ce4ce1
27 changed files with 300 additions and 21 deletions
--- a/vllm/v1/engine/async_llm.py
+++ b/vllm/v1/engine/async_llm.py
@@ -321,6 +321,9 @@ class AsyncLLM(EngineClient):
    async def stop_profile(self) -> None:
        await self.engine_core.profile_async(False)

+    async def reset_prefix_cache(self) -> None:
+        await self.engine_core.reset_prefix_cache_async()
+
    @property
    def is_running(self) -> bool:
        return True