Skip to content

Comments

[WIP] OmniConnector for Multimodal Full Disaggregation#79

Closed
natureofnature wants to merge 2 commits intomainfrom
wzliu_connector_dev
Closed

[WIP] OmniConnector for Multimodal Full Disaggregation#79
natureofnature wants to merge 2 commits intomainfrom
wzliu_connector_dev

Conversation

@natureofnature
Copy link
Contributor

@natureofnature natureofnature commented Nov 21, 2025

Purpose

Supports full E–P–D–G separation across **same process / same node / cross-node **.

Status

On going, currently added mooncake store based connector based on current multiprocessing queue based communication.
A preliminary and draft version for #62.

Test Plan

Test Result


Essential Elements of an Effective PR Description Checklist
  • The purpose of the PR, such as "Fix some issue (link existing issues this PR will resolve)".
  • The test plan, such as providing test command.
  • The test results, such as pasting the results comparison before and after, or e2e results
  • (Optional) The necessary documentation update, such as updating supported_models.md and examples for a new model.
  • (Optional) Release notes update. If your change is user facing, please update the release notes draft.

BEFORE SUBMITTING, PLEASE READ https://github.com/vllm-project/vllm-omni/blob/main/CONTRIBUTING.md (anything written below this line will be removed by GitHub Actions)

ReplicateConfig = None


def k(rid: str, from_stage: str, to_stage: str) -> str:
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

private function?

max_batch_size: 1
engine_args:
model_stage: thinker
model_arch: Qwen2_5OmniForConditionalGeneration
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

it's better for you to add a new example for disaggregated serving and provide a new yaml under examples folder.

Here the yaml is used for defaults

…ni connector to omni-llm, rebased with main (twice).

ray + mooncake connector work on 2 nodes, but needes several updates\n1.start ray inside vllm-omni \n2.placement group optimize \n3.fix close
@natureofnature
Copy link
Contributor Author

closed, refer to #215

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants