diff --git a/tests/perf/stage_configs/qwen3_omni.yaml b/tests/perf/stage_configs/qwen3_omni.yaml index 802f8dd24..fd5586b94 100644 --- a/tests/perf/stage_configs/qwen3_omni.yaml +++ b/tests/perf/stage_configs/qwen3_omni.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: 0.45 enforce_eager: false trust_remote_code: true engine_output_type: latent # Output codec codes for code2wav