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

Enable async_scheduling by default for Qwen3-TTS (#1853)

Browse Source 
Signed-off-by: linyueqian <linyueqian@outlook.com>
This commit is contained in:
Yueqian Lin authored and GitHub committed 2026-03-12 12:30:20 -04:00
1 parent 8ad8988e2b
commit 9c6fbd76be
2 files changed
+4 -4
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

vllm_omni/model_executor/stage_configs/qwen3_tts.yaml
+2 -2
View File
@@ -15,7 +15,7 @@ stage_args:
scheduler_cls: vllm_omni.core.sched.omni_ar_scheduler.OmniARScheduler
enforce_eager: false
trust_remote_code: true
async_scheduling: false
async_scheduling: true
enable_prefix_caching: false
engine_output_type: latent
gpu_memory_utilization: 0.3
@@ -50,7 +50,7 @@ stage_args:
scheduler_cls: vllm_omni.core.sched.omni_generation_scheduler.OmniGenerationScheduler
enforce_eager: true
trust_remote_code: true
async_scheduling: false
async_scheduling: true
enable_prefix_caching: false
engine_output_type: audio
gpu_memory_utilization: 0.2
vllm_omni/model_executor/stage_configs/qwen3_tts_batch.yaml
+2 -2
View File
@@ -19,7 +19,7 @@ stage_args:
scheduler_cls: vllm_omni.core.sched.omni_ar_scheduler.OmniARScheduler
enforce_eager: false
trust_remote_code: true
async_scheduling: false
async_scheduling: true
enable_prefix_caching: false
engine_output_type: latent
gpu_memory_utilization: 0.3
@@ -54,7 +54,7 @@ stage_args:
scheduler_cls: vllm_omni.core.sched.omni_generation_scheduler.OmniGenerationScheduler
enforce_eager: true
trust_remote_code: true
async_scheduling: false
async_scheduling: true
enable_prefix_caching: false
engine_output_type: audio
gpu_memory_utilization: 0.2