tzhouam d7cfe195ea [Enhancement] Refactor OmniARScheduler and OmniGenerationScheduler to include OmniSchedulerOutput ...

- Updated OmniARScheduler to wrap output in OmniSchedulerOutput, including transfer metadata for finished requests needing KV cache transfer.
- Enhanced OmniGenerationScheduler to handle routed experts and finish reasons more effectively, ensuring proper output structure.
- Introduced performance statistics handling in both schedulers for improved monitoring.

Signed-off-by: [Your Name] <your.email@example.com>

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

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

..

assets

Dev/rebase 0.14.0 (#847)

2026-01-21 00:25:25 +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

[Perf] replace torch's conv with vLLM's conv to fix torch 2.9 performance regression (#982)

2026-01-28 10:41:33 +08:00

distributed

[BugFix] Modify the method of obtaining external_request_id (#961)

2026-01-27 20:56:02 +08:00

engine

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

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

entrypoints

Fix TTS speaker typo and add supported languages (#990)

2026-01-27 23:19:51 +08:00

inputs

[Model] Support Qwen3-TTS model series (#895)

2026-01-22 16:57:37 +08:00

lora

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

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

model_executor

[BugFix] Modify the method of obtaining external_request_id (#961)

2026-01-27 20:56:02 +08:00

sample

update dirs

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

utils

[Core]Add GPU Diffusion Runner (#822)

2026-01-17 19:49:13 +08:00

worker

[NPU] Upgrade to v0.14.0 (#820)

2026-01-27 16:45:32 +08:00

__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

[BugFix] Standardize StableAudio audio output (#842)

2026-01-24 22:27:58 +13:00

patch.py

[NPU] Upgrade to v0.14.0 (#820)

2026-01-27 16:45:32 +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