tzhouam 2da9d28f1b Enhance reproducibility in Ulysses attention tests by replacing current_omni_platform.seed_everything with torch's manual_seed and adding support for CUDA devices. Introduce get_supported_tasks method in AsyncOmni class to dynamically determine available tasks based on stage capabilities. ...

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

2026-03-03 09:45:51 +00:00

..

cli

[Feature][Wan2.2] Speed up diffusion model startup by multi-thread weight loading (#1504)

2026-03-02 14:53:25 +00:00

openai

rebase 2026/3/3

2026-03-03 03:50:34 +00:00

__init__.py

[Core] Supports stage abstraction in the diffusion model (#391)

2025-12-27 01:59:33 +13:00

async_omni_diffusion.py

[Feature]: Support cfg kv-cache transfer in multi-stage (#1422)

2026-03-02 05:06:28 +00:00

async_omni_llm.py

rebase 2025/02/16

2026-02-16 03:21:21 +00:00

async_omni.py

Enhance reproducibility in Ulysses attention tests by replacing current_omni_platform.seed_everything with torch's manual_seed and adding support for CUDA devices. Introduce get_supported_tasks method in AsyncOmni class to dynamically determine available tasks based on stage capabilities.

2026-03-03 09:45:51 +00:00

cfg_companion_tracker.py

[Feature]: Support cfg kv-cache transfer in multi-stage (#1422)

2026-03-02 05:06:28 +00:00

chat_utils.py

[Rebase] Rebase to vllm v0.16.0 (#1357)

2026-02-13 18:05:07 +08:00

client_request_state.py

[Feature] Opt metrics structure (#891)

2026-02-09 19:17:32 +08:00

omni_diffusion.py

[Feature]: Support cfg kv-cache transfer in multi-stage (#1422)

2026-03-02 05:06:28 +00:00

omni_llm.py

Merge remote-tracking branch 'origin/main' into dev/vllm-align

2026-02-25 08:15:55 +00:00

omni_stage.py

Merge remote-tracking branch 'origin/main' into dev/vllm-align

2026-03-03 02:57:27 +00:00

omni.py

[Feature]: Support cfg kv-cache transfer in multi-stage (#1422)

2026-03-02 05:06:28 +00:00

stage_utils.py

[Feature]: Support cfg kv-cache transfer in multi-stage (#1422)

2026-03-02 05:06:28 +00:00

utils.py

[Bugfix] Forward all vllm-omni serve command parameters to model (#985)

2026-02-24 22:20:01 +08:00

zmq_utils.py

[Feature] Support Stage Based Deployment CLI (#939)

2026-02-24 16:55:23 +08:00