tzhouam b4fa09f756 Refactor output processing for multimodal capabilities in vLLM-omni ...

- Introduced OmniRequestState to manage multimodal request states.
- Enhanced MultimodalOutputProcessor to handle various output types including images, text, and latents.
- Implemented methods for accumulating multimodal tensors and processing outputs.
- Updated output handling to ensure compatibility with vLLM's base processor while allowing custom modality handlers.

2025-10-22 11:54:07 +08:00

..

config

update ar_dit_test

2025-09-28 21:58:48 +08:00

core

del unnessearcy files

2025-09-29 17:49:32 +08:00

distributed

update dirs

2025-09-11 15:56:28 +08:00

engine

Refactor output processing for multimodal capabilities in vLLM-omni

2025-10-22 11:54:07 +08:00

entrypoints

change omni.py to serve.py and mv to cli

2025-09-29 18:10:37 +08:00

model_executor

update ar_dit_test

2025-09-28 21:58:48 +08:00

sample

update dirs

2025-09-11 15:43:43 +08:00

utils

Initial vLLM-omni repository structure

2025-09-11 14:32:51 +08:00

worker

update ar_dit_test

2025-09-28 21:58:48 +08:00

__init__.py

refactor: move omni_llm.py to entrypoints directory

2025-09-26 17:39:00 +08:00

request.py

init request.py

2025-09-15 22:46:40 +08:00