anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

[cpu worker] yaml update

Browse Source 
Signed-off-by: 齐保元 <qibaoyuan@xiaomi.com>
This commit is contained in:
齐保元 committed 2025-11-14 18:44:29 +08:00
1 parent 8ee1d73d02
commit ac149f6ea9
1 file changed
+3 -3
Download Patch File Download Diff File Expand all files Collapse all files
vllm_omni/model_executor/stage_configs/qwen2_5_omni.yaml
+3 -3
View File
@@ -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