[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/engine/async_llm_engine.py
+++ b/vllm/engine/async_llm_engine.py
@@ -1182,6 +1182,9 @@ class AsyncLLMEngine(EngineClient):
    async def stop_profile(self) -> None:
        self.engine.stop_profile()

+    async def reset_prefix_cache(self) -> None:
+        self.engine.reset_prefix_cache()
+
    async def add_lora(self, lora_request: LoRARequest) -> None:
        self.engine.add_lora(lora_request)