[BUG] Reset running requests when clearing cache for pause/resume (#34382)

Signed-off-by: hao-aaron <ahao@anyscale.com>
2026-02-12 08:19:13 -08:00
parent dea63512bb
commit 7b5a8b4a9d
1 changed files with 1 additions and 1 deletions
--- a/vllm/v1/engine/async_llm.py
+++ b/vllm/v1/engine/async_llm.py
@@ -793,7 +793,7 @@ class AsyncLLM(EngineClient):

        # Clear cache
        if clear_cache:
-            await self.reset_prefix_cache()
+            await self.reset_prefix_cache(reset_running_requests=True)
            await self.reset_mm_cache()
            await self.reset_encoder_cache()