tzhouam 3208afd82b Refactor OmniRequestOutput to encapsulate multimodal output ...

- Changed the multimodal_output field to a private attribute _multimodal_output for better encapsulation.
- Added a property method to access multimodal_output, allowing for a clearer interface and improved handling of request outputs.

Signed-off-by: [Your Name] <[Your Email]>

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

2026-01-30 10:02:22 +00:00

..

assets

Dev/rebase 0.14.0 (#847)

2026-01-21 00:25:25 +08:00

benchmarks

[Benchmark] Add vLLM-Omni Omni model online benchmark (#780)

2026-01-30 11:41:09 +08:00

config

[Enhancement] Add mm_encoder_only parameter and deprecation warning for convert option

2026-01-28 15:40:29 +08:00

core

[Enhancement] Refactor OmniARScheduler and OmniGenerationScheduler to include OmniSchedulerOutput

2026-01-28 15:40:59 +08:00

diffusion

[Feat] Support XPU Backend in vLLM-Omni (#191)

2026-01-30 04:33:05 +13:00

distributed

[BugFix] Fix the accuracy issue of multimodal input. (#1020)

2026-01-29 19:30:11 +08:00

engine

Merge branch 'main' into dev/vllm-align

2026-01-30 02:53:03 +00:00

entrypoints

Fix audio tensor extraction in end2end.py files across multiple examples

2026-01-30 10:00:14 +00:00

inputs

Refactor OmniInputPreprocessor to remove unused embed processing logic

2026-01-30 03:02:38 +00:00

lora

[Feature] Diffusion LoRA Adapter Support (PEFT compatible) for vLLM alignment (#758)

2026-01-27 10:22:40 +08:00

model_executor

Merge branch 'main' into dev/vllm-align

2026-01-30 02:53:03 +00:00

platforms

[Feat] Support XPU Backend in vLLM-Omni (#191)

2026-01-30 04:33:05 +13:00

plugins

[Hardware] Support platforms and plugin system (#774)

2026-01-28 22:12:52 +08:00

sample

update dirs

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

utils

[Hardware] Support platforms and plugin system (#774)

2026-01-28 22:12:52 +08:00

worker

Merge branch 'main' into dev/vllm-align

2026-01-30 02:53:03 +00:00

__init__.py

Support Bagel Model (#726)

2026-01-22 23:09:55 +13:00

logger.py

[BugFix] Failed to print DEBUG level log (#307)

2025-12-15 07:13:36 +00:00

outputs.py

Refactor OmniRequestOutput to encapsulate multimodal output

2026-01-30 10:02:22 +00:00

patch.py

Remove commented-out import and related code for MRotaryEmbedding in patch.py to clean up the codebase.

2026-01-28 16:52:10 +08:00

request.py

[Enhancement] Update OmniRequest to support torch.Tensor for prompt_embeds and add decoding method

2026-01-28 15:40:17 +08:00

version.py

Bump version to 0.14.0rc1 (#910)

2026-01-22 17:09:48 -08:00