Refactor OmniEngineArgs and AsyncOmniEngineArgs to improve compatibility with partial payloads by using getattr for various attributes. Update GPUGenerationModelRunner and OmniGPUModelRunner to replace the activate_lora parameter with num_active_loras for better clarity and backward compatibility. This change enhances the handling of LoRA activation during model runs.

Signed-off-by: tzhouam <tzhouam@connect.ust.hk>

vllm_omni/model_executor/models/qwen3_omni/qwen3_omni_moe_thinker.py

@@ -144,7 +144,6 @@ class Qwen3MoeLLMModel(_Qwen3MoeLLMModel):
         positions: torch.Tensor,
         intermediate_tensors: IntermediateTensors | None = None,
         inputs_embeds: torch.Tensor | None = None,
-        *,
         capture_layer_indices: Sequence[int] | None = None,
         return_hidden_states: bool = False,
         deepstack_input_embeds: IntermediateTensors | None = None,