[Docs] CLI Docs updates#2978
Merged
Merged
Conversation
|
Codex usage limits have been reached for code reviews. Please check with the admins of this repo to increase the limits by adding credits. |
Collaborator
|
LGTM. @princepride PTAL as it touched bagel's code. |
Contributor
There was a problem hiding this comment.
Pull request overview
Updates vLLM-Omni documentation and test helpers to better document and exercise the “stage-based CLI” (one stage per process) and to clarify when to use --deploy-config vs the legacy --stage-configs-path.
Changes:
- Added stage-based CLI quickstart/quick-reference docs across CLI docs, stage config docs, and model example pages (Qwen3-Omni, BAGEL).
- Updated BAGEL examples to use
--omni-master-address/--omni-master-port(instead of-oma/-omp) and documented legacy vs migrated config flags. - Updated test runtime helpers to choose
--deploy-configvs--stage-configs-pathbased on YAML schema, with new unit tests covering the selection.
Reviewed changes
Copilot reviewed 10 out of 10 changed files in this pull request and generated 3 comments.
Show a summary per file
| File | Description |
|---|---|
tests/helpers/test_runtime.py |
Adds unit tests for the new CLI-flag selection helper and stage CLI command building. |
tests/helpers/runtime.py |
Introduces get_server_config_cli_args() and uses it in OmniServerStageCli command construction. |
tests/helpers/fixtures/runtime.py |
Uses get_server_config_cli_args() so fixtures exercise the correct user-facing CLI flag. |
examples/online_serving/qwen3_omni/README.md |
Adds stage-based CLI instructions and guidance on when to use --deploy-config vs --stage-overrides. |
examples/online_serving/bagel/run_server_stage_cli.sh |
Switches to long-form --omni-master-* flags for stage-based launch script. |
examples/online_serving/bagel/README.md |
Clarifies BAGEL remains legacy stage_args and updates stage-based CLI instructions accordingly. |
docs/user_guide/examples/online_serving/qwen3_omni.md |
Mirrors Qwen3-Omni stage-based CLI docs in rendered documentation. |
docs/user_guide/examples/online_serving/bagel.md |
Mirrors BAGEL stage-based CLI + legacy config flag guidance in rendered documentation. |
docs/configuration/stage_configs.md |
Adds a stage-based CLI quick reference and updates examples to prefer --deploy-config for new schema. |
docs/cli/serve.md |
Adds a stage-based CLI quickstart section to the serve CLI docs. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Collaborator
|
I have a pr will remove bagel's stage yaml file: #2936 |
Collaborator
|
@wuhang2014 Please coordinate with @princepride |
Contributor
Author
Contributor
There was a problem hiding this comment.
Pull request overview
Updates documentation and example scripts to describe and demonstrate the stage-based CLI workflow for multi-stage Omni serving, and standardizes the master address/port flags across docs/examples.
Changes:
- Add stage-based CLI quickstart and guidance (including
--stage-id, master address/port, and when to use--stage-overrides). - Update BAGEL stage-based launcher script/docs to use
--omni-master-address/--omni-master-portinstead of-oma/-omp. - Refresh Qwen3-Omni and stage-config documentation around default deploy YAML resolution and override patterns.
Reviewed changes
Copilot reviewed 7 out of 7 changed files in this pull request and generated 6 comments.
Show a summary per file
| File | Description |
|---|---|
| examples/online_serving/qwen3_omni/README.md | Adds stage-based CLI launch instructions and deploy-config guidance for Qwen3-Omni. |
| examples/online_serving/bagel/run_server_stage_cli.sh | Switches master flags to long-form --omni-master-* in the stage CLI script. |
| examples/online_serving/bagel/README.md | Updates BAGEL multi-node instructions and flag names for stage-based runs. |
| docs/user_guide/examples/online_serving/qwen3_omni.md | Mirrors Qwen3-Omni stage-based CLI instructions into the user guide. |
| docs/user_guide/examples/online_serving/bagel.md | Mirrors BAGEL stage-based launch flag updates into the user guide. |
| docs/configuration/stage_configs.md | Adds stage-based CLI section and clarifies deploy-config vs stage-configs-path usage. |
| docs/cli/serve.md | Adds a stage-based CLI quickstart section to the serve CLI docs. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Comment on lines
+3
to
+8
| ## Stage-based CLI quickstart | ||
|
|
||
| The stage-based CLI is designed for deployments that require launching each pipeline stage in an isolated process | ||
| (e.g., across separate operating system processes, distinct GPUs, or distributed hosts). | ||
|
|
||
| - For **migrated models** that utilize the bundled deployment YAML configurations located in |
wuhang2014
force-pushed
the
doc_cli
branch
3 times, most recently
from
8ba003b to
fd948e6
Compare
| If you have a custom stage configs file, launch the server with the command below: | ||
|
|
||
| ```bash | ||
| vllm serve ByteDance-Seed/BAGEL-7B-MoT --omni --port 8091 --stage-configs-path /path/to/stage_configs_file |
Collaborator
There was a problem hiding this comment.
do we still need to keep this?
Contributor
Author
There was a problem hiding this comment.
#2936 by @princepride will handle docs relative with Bagel
| @@ -12,21 +12,80 @@ Please refer to [README.md](../../../README.md) | |||
| vllm serve Qwen/Qwen3-Omni-30B-A3B-Instruct --omni --port 8091 | |||
Collaborator
There was a problem hiding this comment.
can you update the qwen3_omni recipe? we will rm model specific examples here and only keep x2y.py for different modalities
Contributor
Author
There was a problem hiding this comment.
Sure, I've updated recipes of qwen3_omni.
Signed-off-by: wuhang <wuhang6@huawei.com>
Signed-off-by: wuhang <wuhang6@huawei.com>
Signed-off-by: wuhang <wuhang6@huawei.com>
Contributor
|
LGTM |
princepride
added a commit
to princepride/vllm-omni
that referenced
this pull request
Apr 24, 2026
Resolve conflicts in docs/user_guide/examples/online_serving/bagel.md and examples/online_serving/bagel/README.md by keeping the restructured --deploy-config docs from this PR and dropping the stage-configs-path references reintroduced by upstream vllm-project#2978. Signed-off-by: princepride <wangzhipeng628@gmail.com>
lengrongfu
pushed a commit
to lengrongfu/vllm-omni
that referenced
this pull request
May 1, 2026
Signed-off-by: wuhang <wuhang6@huawei.com>
clodaghwalsh17
pushed a commit
to clodaghwalsh17/nm-vllm-omni-ent
that referenced
this pull request
May 12, 2026
Signed-off-by: wuhang <wuhang6@huawei.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
PLEASE FILL IN THE PR DESCRIPTION HERE ENSURING ALL CHECKLIST ITEMS (AT THE BOTTOM) HAVE BEEN CONSIDERED.
Purpose
#1462
Test Plan
Test Result
Essential Elements of an Effective PR Description Checklist
supported_models.mdandexamplesfor a new model. Please runmkdocs serveto sync the documentation editions to./docs.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)