From 761020a2558ab14147b3eb678ca8f1eebb92a563 Mon Sep 17 00:00:00 2001 From: Siyuan Liu Date: Sun, 11 May 2025 23:28:52 +0000 Subject: [PATCH] fix a bug in runner Signed-off-by: Siyuan Liu --- vllm/v1/worker/tpu_model_runner.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/vllm/v1/worker/tpu_model_runner.py b/vllm/v1/worker/tpu_model_runner.py index 983f8707a245..687dabee2290 100644 --- a/vllm/v1/worker/tpu_model_runner.py +++ b/vllm/v1/worker/tpu_model_runner.py @@ -531,7 +531,7 @@ def _prepare_inputs(self, scheduler_output: "SchedulerOutput"): np.add(block_numbers * self.block_size, block_offsets, out=self.input_batch.block_table. - slot_mapping_cpu[:total_num_scheduled_tokens]) + slot_mapping_np[:total_num_scheduled_tokens]) # Prepare the attention metadata. self.query_start_loc_np[0] = 0