tzhouam 3265e857eb Refactor OmniLLM and MultimodalOutputProcessor initialization ...

- Removed AsyncOmniLLM from the main entry points as it is not supported yet.
- Updated the constructor of MultimodalOutputProcessor to set a default value for engine_core_output_type.
- Adjusted output type handling in various methods to utilize the new default engine_core_output_type for consistency.

2025-10-24 17:15:34 +08:00

..

__init__.py

Add Omni model components and input processing for hidden states support

2025-10-22 15:16:25 +08:00

arg_utils.py

Apply suggestion from @Copilot

2025-10-24 11:14:58 +08:00

diffusion_engine.py

add back the diffusion engine as a placeholder for the actural diffusion engine in the future

2025-10-23 10:04:27 +08:00

output_processor.py

Refactor OmniLLM and MultimodalOutputProcessor initialization

2025-10-24 17:15:34 +08:00

processor.py

Add dtype mapping method in OmniProcessor

2025-10-24 11:40:43 +08:00