From 7d06dd1ffaab13bb6b9a34e86a8a62e4d715bd1e Mon Sep 17 00:00:00 2001 From: Taneem Ibrahim Date: Mon, 21 Sep 2026 18:54:57 -0500 Subject: [PATCH] [Pooling] MRV2 pooling shutdown model ref (#57737) Signed-off-by: Taneem Ibrahim --- vllm/v1/worker/gpu/model_runner.py | 1 + 1 file changed, 1 insertion(+) diff --git a/vllm/v1/worker/gpu/model_runner.py b/vllm/v1/worker/gpu/model_runner.py index 92a37008ce..8be523d3de 100644 --- a/vllm/v1/worker/gpu/model_runner.py +++ b/vllm/v1/worker/gpu/model_runner.py @@ -2245,6 +2245,7 @@ class GPUModelRunner(LoRAModelRunnerMixin): self.aux_output_connector.close() self.cudagraph_manager = None self.fast_prefill = None + self.pooling_runner = None if hasattr(self, "kv_caches"): self.kv_caches.clear() if hasattr(self, "attn_groups"):