Skip to content

[skip ci][doc]Update async_chunk design diagram#2420

Merged
hsliuustc0106 merged 1 commit into
vllm-project:mainfrom
amy-why-3459:bugfix
Apr 13, 2026
Merged

[skip ci][doc]Update async_chunk design diagram#2420
hsliuustc0106 merged 1 commit into
vllm-project:mainfrom
amy-why-3459:bugfix

Conversation

@amy-why-3459
Copy link
Copy Markdown
Contributor

PLEASE FILL IN THE PR DESCRIPTION HERE ENSURING ALL CHECKLIST ITEMS (AT THE BOTTOM) HAVE BEEN CONSIDERED.

Purpose

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. Please provide the test scripts & test commands. Please state the reasons if your codes don't require additional test scripts. For test file guidelines, please check the test style doc
  • The test results. Please paste the results comparison before and after, or the e2e results.
  • (Optional) The necessary documentation update, such as updating supported_models.md and examples for a new model. Please run mkdocs serve to sync the documentation editions to ./docs.
  • (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)

@amy-why-3459 amy-why-3459 changed the title [doc][skip ci]Update async_chunk design diagram [doc]Update async_chunk design diagram Apr 1, 2026
@amy-why-3459 amy-why-3459 force-pushed the bugfix branch 2 times, most recently from 95e476e to fd71950 Compare April 2, 2026 01:48
@amy-why-3459
Copy link
Copy Markdown
Contributor Author

@R2-Y @Shirley125 PTAL

[Thinker: ████████████████████] (2.0s)
[Talker: ████████████████████] (3.0s)
[Code2Wav: ████] (1.0s)
Total: 6.0s, TTFA: 6.0s
Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

maybe change TTFA to TTFP? consistent with qwen3-omni paper

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

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

fixed

[Thinker: ████░░░░████░░░░████] (2.0s, streaming)
[Talker: ░░████░░░░████░░] (3.0s, parallel)
[Code2Wav: ░░░░████░░] (1.0s, batched)
Total: ~3.5s, TTFA: ~0.5s
Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

same as above

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

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

fixed

**Diagram Legend:**
| Color | Stage Type | Description |
|:------|:-----------|:------------|
| 🟪 Pink (`prefill`) | Initialization | Context processing, KV cache initialization |
Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

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

the color looks not the same as diagram

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

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

fixed

Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com>
@gcanlin gcanlin added the ready label to trigger buildkite CI label Apr 11, 2026
Copy link
Copy Markdown
Collaborator

@gcanlin gcanlin left a comment

Choose a reason for hiding this comment

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

Curious, from the new diagram, the talker prefill is outputting the second text token. Is it expected? I don't understand it fully.

@hsliuustc0106 hsliuustc0106 changed the title [doc]Update async_chunk design diagram [skip ci][doc]Update async_chunk design diagram Apr 13, 2026
@hsliuustc0106 hsliuustc0106 merged commit 2a1d506 into vllm-project:main Apr 13, 2026
6 checks passed
Celeste-jq pushed a commit to IsleOfDawnlight/vllm-omni-voxcpm that referenced this pull request Apr 14, 2026
Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com>
lengrongfu pushed a commit to lengrongfu/vllm-omni that referenced this pull request May 1, 2026
Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com>
clodaghwalsh17 pushed a commit to clodaghwalsh17/nm-vllm-omni-ent that referenced this pull request May 12, 2026
Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

ready label to trigger buildkite CI

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants