Skip to content

Conversation

@leo-pony
Copy link
Collaborator

@leo-pony leo-pony commented Nov 26, 2025

What this PR does / why we need it?

Fix the ray start failed bug: local_world_size cannot little than visible device count error
detail see issue #4456.

This fix code is copied from vllm fixing modify, PR: #28873

Does this PR introduce any user-facing change?

How was this patch tested?

Copy link
Contributor

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

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

Code Review

This pull request fixes a bug where ray start would fail due to an incorrect assertion on local_world_size. The change correctly adds a condition to skip this assertion when using ray or external_launcher as the distributed backend. The fix seems correct and addresses the issue described. I have one suggestion to improve code consistency and readability.

@github-actions
Copy link

👋 Hi! Thank you for contributing to the vLLM Ascend project. The following points will speed up your PR merge:‌‌

  • A PR should do only one thing, smaller PRs enable faster reviews.
  • Every PR should include unit tests and end-to-end tests ‌to ensure it works and is not broken by other future PRs.
  • Write the commit message by fulfilling the PR description to help reviewer and future developers understand.

If CI fails, you can run linting and testing checks locally according Contributing and Testing.

@leo-pony
Copy link
Collaborator Author

leo-pony commented Nov 26, 2025

@wangxiyuan It's ready for review. Could your help review?
Test case:
I test with 2 * atlas A3 nodes, with pp2 * tp16, successfully starting and running inference:
Ray start successfully, and qwen3-235B-30B successully running:
4e5b8b0c-4d78-4fc9-a693-f0f15fb5ccc8
d465d430-dfd2-4166-a327-358e3c1314fd
The inference request successfully returned:
c5f3d578-83b6-4a3e-9448-bc06e1d22360

Signed-off-by: leo-pony <[email protected]>
@leo-pony leo-pony added ready read for review ready-for-test start test by label for PR labels Nov 27, 2025
@wangxiyuan wangxiyuan merged commit 89a1a65 into vllm-project:main Nov 27, 2025
47 of 48 checks passed
ChenCangtao pushed a commit to ChenCangtao/vllm-ascend that referenced this pull request Dec 3, 2025
…sible device count error (vllm-project#4457)

### What this PR does / why we need it?
Fix the ray start failed bug: local_world_size cannot little than
visible device count error
detail see issue vllm-project#4456.

This fix code is copied from vllm fixing modify, PR:
[#28873](vllm-project/vllm#28873)


- vLLM version: v0.11.2
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.2

---------

Signed-off-by: leo-pony <[email protected]>
Mercykid-bash pushed a commit to Mercykid-bash/vllm-ascend that referenced this pull request Dec 4, 2025
…sible device count error (vllm-project#4457)

### What this PR does / why we need it?
Fix the ray start failed bug: local_world_size cannot little than
visible device count error
detail see issue vllm-project#4456.

This fix code is copied from vllm fixing modify, PR:
[#28873](vllm-project/vllm#28873)

- vLLM version: v0.11.2
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.2

---------

Signed-off-by: leo-pony <[email protected]>
Signed-off-by: Che Ruan <[email protected]>
Mercykid-bash pushed a commit to Mercykid-bash/vllm-ascend that referenced this pull request Dec 4, 2025
…sible device count error (vllm-project#4457)

### What this PR does / why we need it?
Fix the ray start failed bug: local_world_size cannot little than
visible device count error
detail see issue vllm-project#4456.

This fix code is copied from vllm fixing modify, PR:
[#28873](vllm-project/vllm#28873)

- vLLM version: v0.11.2
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.2

---------

Signed-off-by: leo-pony <[email protected]>
Signed-off-by: Che Ruan <[email protected]>
Meihan-chen pushed a commit to Meihan-chen/vllm-ascend that referenced this pull request Dec 5, 2025
…sible device count error (vllm-project#4457)

### What this PR does / why we need it?
Fix the ray start failed bug: local_world_size cannot little than
visible device count error
detail see issue vllm-project#4456.

This fix code is copied from vllm fixing modify, PR:
[#28873](vllm-project/vllm#28873)


- vLLM version: v0.11.2
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.2

---------

Signed-off-by: leo-pony <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

module:tests ready read for review ready-for-test start test by label for PR

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants