From c8b695f1810205805ad11aa2eaef9a75ca7dfe3e Mon Sep 17 00:00:00 2001 From: Taichang Zhou Date: Sun, 8 Mar 2026 01:48:42 +0800 Subject: [PATCH] smaller talker gpu util to avoid oom Signed-off-by: Taichang Zhou --- tests/e2e/stage_configs/qwen3_omni_ci.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tests/e2e/stage_configs/qwen3_omni_ci.yaml b/tests/e2e/stage_configs/qwen3_omni_ci.yaml index 641fc77ae..45e7fcab8 100644 --- a/tests/e2e/stage_configs/qwen3_omni_ci.yaml +++ b/tests/e2e/stage_configs/qwen3_omni_ci.yaml @@ -47,7 +47,7 @@ stage_args: model_arch: Qwen3OmniMoeForConditionalGeneration worker_type: ar scheduler_cls: vllm_omni.core.sched.omni_ar_scheduler.OmniARScheduler - gpu_memory_utilization: 0.6 + gpu_memory_utilization: 0.5 enforce_eager: false trust_remote_code: true engine_output_type: latent # Output codec codes for code2wav