Files
vllm-omni/examples/online_serving/qwen3_omni/qwen3_omni_moe_thinking.yaml
T
2026-03-20 16:13:24 +08:00

37 lines
1.1 KiB
YAML

# Stage config for running Qwen3-Omni-MoE-Thinking (text-only output)
# This config is for models like Qwen3-Omni-30B-A3B-Thinking that only have the
# thinker component and do not support audio output.
#
# Single stage: Thinker (multimodal understanding + text generation)
# The following config has been verified on 2x H100-80G GPUs.
stage_args:
- stage_id: 0
runtime:
devices: "0,1"
engine_args:
model_stage: thinker
max_num_seqs: 1
model_arch: Qwen3OmniMoeForConditionalGeneration
worker_type: ar
scheduler_cls: vllm_omni.core.sched.omni_ar_scheduler.OmniARScheduler
gpu_memory_utilization: 0.9
enforce_eager: true
trust_remote_code: true
engine_output_type: text
distributed_executor_backend: "mp"
enable_prefix_caching: false
hf_config_name: thinker_config
tensor_parallel_size: 2
final_output: true
final_output_type: text
is_comprehension: true
default_sampling_params:
temperature: 0.4
top_p: 0.9
top_k: 1
max_tokens: 2048
seed: 42
detokenize: True
repetition_penalty: 1.05