From a114bf20a3ef3c03ee6fc127cde0d1422de4be6c Mon Sep 17 00:00:00 2001 From: SnowCharm Date: Tue, 22 Apr 2025 14:01:54 +0800 Subject: [PATCH] [Perf] Optimize `_update_states` for GPU model runner (#16910) Signed-off-by: snowcharm --- vllm/v1/worker/gpu_model_runner.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/vllm/v1/worker/gpu_model_runner.py b/vllm/v1/worker/gpu_model_runner.py index d5efe2dda16d0..bdf0d0f72289e 100644 --- a/vllm/v1/worker/gpu_model_runner.py +++ b/vllm/v1/worker/gpu_model_runner.py @@ -454,7 +454,7 @@ class GPUModelRunner(LoRAModelRunnerMixin): # Add the new or resumed requests to the persistent batch. # The smaller empty indices are filled first. - removed_req_indices = sorted(removed_req_indices, reverse=True) + removed_req_indices.sort(reverse=True) for req_id in req_ids_to_add: req_state = self.requests[req_id] if removed_req_indices: