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

[CI] Add Qwen3-omni offline UT (#216)

Browse Source 
Signed-off-by: Rein Yang <ruiruyang2@gmail.com>
This commit is contained in:
rein yang authored and GitHub committed 2025-12-08 18:11:39 +08:00
1 parent 892f837c5a
commit baf1086d55
10 files changed
+314 -9
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

docs/configuration/stage_configs/qwen2_5_omni.yaml
+2 -2
View File
@@ -9,7 +9,7 @@ stage_args:
model_stage: thinker
model_arch: Qwen2_5OmniForConditionalGeneration
worker_cls: vllm_omni.worker.gpu_ar_worker.GPUARWorker
scheduler_cls: vllm_omni.core.sched.scheduler.OmniScheduler
scheduler_cls: vllm_omni.core.sched.omni_ar_scheduler.OmniARScheduler
gpu_memory_utilization: 0.8
enforce_eager: true # Now we only support eager mode
trust_remote_code: true
@@ -35,7 +35,7 @@ stage_args:
model_stage: talker
model_arch: Qwen2_5OmniForConditionalGeneration
worker_cls: vllm_omni.worker.gpu_ar_worker.GPUARWorker
scheduler_cls: vllm_omni.core.sched.scheduler.OmniScheduler
scheduler_cls: vllm_omni.core.sched.omni_ar_scheduler.OmniARScheduler
gpu_memory_utilization: 0.8
enforce_eager: true
trust_remote_code: true