[Doc] Add --shm-size option to Docker command for qwen3 vl 235B #3519
Conversation
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
github-actions
bot
added
the
documentation
|
👋 Hi! Thank you for contributing to the vLLM Ascend project. The following points will speed up your PR merge:
If CI fails, you can run linting and testing checks locally according Contributing and Testing. |
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Code Review
This pull request adds the --shm-size option to the Docker run command in the multi_node_qwen3vl.md documentation file. This change aims to prevent potential core dumps of the vllm:EngineCore process under high workloads by increasing the shared memory size. I have added a review comment to address a potential issue.
Added shared memory size option to Docker run command.If shm-size is not specified, docker will use 64MB by default. In this case, vllm:EngineCore process may coredump if workload is high. Signed-off-by: likeful <irayki@gmail.com>
Signed-off-by: likeful <irayki@gmail.com> Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Yikun
reviewed
Oct 18, 2025
| --device /dev/davinci_manager \ | ||
| --device /dev/devmm_svm \ | ||
| --device /dev/hisi_hdc \ | ||
| --shm-size=1000g # Adjust based on workload. Consider using a smaller value if memory is constrained. |
Collaborator
There was a problem hiding this comment.
- This cmd can't be excute after this fix.
Suggested change
| --shm-size=1000g # Adjust based on workload. Consider using a smaller value if memory is constrained. | |
| --shm-size=4g \ |
- What's the recommanded value of
shm-sizeand setting rule? just saw [1] has many different examples.
[1] https://docs.vllm.ai/en/latest/cli/run-batch.html?q=shm-size
Contributor
Author
There was a problem hiding this comment.
We assume this configuration depends on workloads, in `Qwen3-VL-235B-A22B-Instruct and multiple nodes scenario, suggest set shm-size start from 256g, with 8g or 16g incremental step
Signed-off-by: leijie2015 <irayki@gmail.com>
Yikun
approved these changes
Oct 20, 2025
leijie-cn
changed the title
leijie-cn
changed the title
Yikun
changed the title
Yikun
changed the title
Yikun
changed the title
ZYang6263
pushed a commit
to rjg-lyh/vllm-ascend
that referenced
this pull request
Oct 23, 2025
…-project#3519) ### What this PR does / why we need it? Added shared memory size option to Docker run command.If shm-size is not specified, docker will use 64MB by default. In this case, vllm:EngineCore process may coredump if workload is high. ### Does this PR introduce _any_ user-facing change? No ### How was this patch tested? Done Closes: vllm-project#3513 - vLLM version: v0.11.0rc3 - vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.0 --------- Signed-off-by: likeful <irayki@gmail.com> Signed-off-by: leijie2015 <irayki@gmail.com> Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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.
What this PR does / why we need it?
Added shared memory size option to Docker run command.If shm-size is not specified, docker will use 64MB by default. In this case, vllm:EngineCore process may coredump if workload is high.
Does this PR introduce any user-facing change?
No
How was this patch tested?
Done
Closes: #3513