From ac149f6ea9cee78db4d8680cfeb0a8447f9be68b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E9=BD=90=E4=BF=9D=E5=85=83?= Date: Fri, 14 Nov 2025 17:40:56 +0800 Subject: [PATCH] [cpu worker] yaml update MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: 齐保元 --- vllm_omni/model_executor/stage_configs/qwen2_5_omni.yaml | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/vllm_omni/model_executor/stage_configs/qwen2_5_omni.yaml b/vllm_omni/model_executor/stage_configs/qwen2_5_omni.yaml index 620da3a89..b41524683 100644 --- a/vllm_omni/model_executor/stage_configs/qwen2_5_omni.yaml +++ b/vllm_omni/model_executor/stage_configs/qwen2_5_omni.yaml @@ -8,7 +8,7 @@ stage_args: engine_args: model_stage: thinker model_arch: Qwen2_5OmniForConditionalGeneration - worker_cls: vllm_omni.worker.gpu_ar_worker.GPUARWorker + worker_cls: vllm_omni.worker.gpu.gpu_ar_worker.GPUARWorker scheduler_cls: vllm_omni.core.sched.scheduler.OmniScheduler gpu_memory_utilization: 0.8 enforce_eager: true # need to discuss @@ -25,7 +25,7 @@ stage_args: engine_args: model_stage: talker model_arch: Qwen2_5OmniForConditionalGeneration - worker_cls: vllm_omni.worker.gpu_ar_worker.GPUARWorker + worker_cls: vllm_omni.worker.gpu.gpu_ar_worker.GPUARWorker scheduler_cls: vllm_omni.core.sched.scheduler.OmniScheduler gpu_memory_utilization: 0.8 enforce_eager: true @@ -42,7 +42,7 @@ stage_args: engine_args: model_stage: code2wav model_arch: Qwen2_5OmniForConditionalGeneration - worker_cls: vllm_omni.worker.gpu_diffusion_worker.GPUDiffusionWorker + worker_cls: vllm_omni.worker.gpu.gpu_diffusion_worker.GPUDiffusionWorker scheduler_cls: vllm_omni.core.sched.diffusion_scheduler.DiffusionScheduler gpu_memory_utilization: 0.15 enforce_eager: true