From 40d86ee412eeeca93e0c37432db6b96829cb64e2 Mon Sep 17 00:00:00 2001 From: Chengji Yao Date: Thu, 24 Jul 2025 23:01:53 -0700 Subject: [PATCH] [TPU][Bugfix] fix OOM issue in CI test (#21550) Signed-off-by: Chengji Yao --- tests/v1/tpu/test_basic.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tests/v1/tpu/test_basic.py b/tests/v1/tpu/test_basic.py index 865b58bc7f4b0..dd89059ded524 100644 --- a/tests/v1/tpu/test_basic.py +++ b/tests/v1/tpu/test_basic.py @@ -59,7 +59,7 @@ def test_basic( # actually test chunked prompt max_num_batched_tokens=1024, max_model_len=8192, - gpu_memory_utilization=0.7, + gpu_memory_utilization=0.95, max_num_seqs=max_num_seqs, tensor_parallel_size=tensor_parallel_size) as vllm_model: vllm_outputs = vllm_model.generate_greedy(example_prompts,