tzhouam cc4ade4ba7 Refactor shutdown logic in OmniLLM and stage worker to ensure proper engine closure. The shutdown method now checks for the presence of engine_core before invoking shutdown, enhancing resource management. Additionally, the stage worker now explicitly calls stage_engine.close() upon receiving a shutdown signal. This improves the overall stability and reliability of the shutdown process. ...

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

2026-03-17 08:19:56 +00:00

..

cli

rebase: align vllm-omni with vLLM e9163b536e72

2026-03-16 02:32:39 +00:00

openai

Update Dockerfile.ci to use a new vllm wheel URL and refactor MooncakeConnector import logic in monkey_patch.py for improved compatibility. Adjust OpenAIServingChat to call the harmony request method from the correct context.

2026-03-16 08:33:28 +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

[Feat] Enable expert parallel for diffusion MoE layers (#1323)

2026-03-11 10:45:36 +08:00

async_omni_llm.py

Dev/rebase v0170 (#1639)

2026-03-09 17:29:38 +08:00

async_omni.py

[Bugfix] Fix cpu offload and quantization compatibility (#1473)

2026-03-14 18:55:30 +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

[Diffusion] [Model] Dreamid omni (#1855)

2026-03-13 21:53:06 +08:00

omni_llm.py

Refactor shutdown logic in OmniLLM and stage worker to ensure proper engine closure. The shutdown method now checks for the presence of engine_core before invoking shutdown, enhancing resource management. Additionally, the stage worker now explicitly calls stage_engine.close() upon receiving a shutdown signal. This improves the overall stability and reliability of the shutdown process.

2026-03-17 08:19:56 +00:00

omni_stage.py

Refactor shutdown logic in OmniLLM and stage worker to ensure proper engine closure. The shutdown method now checks for the presence of engine_core before invoking shutdown, enhancing resource management. Additionally, the stage worker now explicitly calls stage_engine.close() upon receiving a shutdown signal. This improves the overall stability and reliability of the shutdown process.

2026-03-17 08:19:56 +00:00

omni.py

[Config Refactor][1/2] Model Pipeline Configuration System (#1115)

2026-03-12 21:09:34 +08:00

pd_utils.py

[Feature] Split #1303 Part 1: PD disaggregation scaffolding (#1863)

2026-03-16 14:05:19 +08:00

stage_utils.py

[Config Refactor][1/2] Model Pipeline Configuration System (#1115)

2026-03-12 21:09:34 +08:00

utils.py

[Config Refactor][1/2] Model Pipeline Configuration System (#1115)

2026-03-12 21:09:34 +08:00

zmq_utils.py

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

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