vllm_omni.model_executor.models.qwen3_omni ¶
Modules:
| Name | Description |
|---|---|
duplex | |
pipeline | Qwen3-Omni-MoE pipeline topology (frozen). |
quantization | Quantization mapping helpers for nested Qwen3-Omni stages. |
qwen3_omni | Inference-only Qwen3-Omni-Moe unified model (thinker + talker + code2wav). |
qwen3_omni_code2wav | Inference-only Qwen3-Omni-Moe Code2Wav model. |
qwen3_omni_moe_code_predictor_mtp | Qwen3-Omni Code Predictor -- thin wrapper over CodePredictorWrapper. |
qwen3_omni_moe_talker | |
qwen3_omni_moe_thinker | Inference-only Qwen3-Omni-Moe model (thinker part). |