[Doc] Add deepseek multi node doc #3223
Draft
+212
−0
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
|
👋 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. |
github-actions
bot
added
the
documentation
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request adds documentation for multi-node deployment of DeepSeek models. The new documentation file multi_node_deepseek.md contains several critical and high-severity issues that would prevent users from successfully following the tutorials. My review includes corrections for:
- Incorrect device mappings in the
docker runcommand for the specified hardware. - Inconsistent and incorrect model configurations in the multi-node
BF16tutorial, including model name, batch token limits, and environment variables. - A misleading comment in the
BF16tutorial. - A confusing documentation structure where a single-node tutorial is placed within a multi-node guide.
Applying these suggestions will significantly improve the correctness and clarity of the documentation.
MengqingCao
reviewed
Sep 29, 2025
MengqingCao
reviewed
Sep 29, 2025
MengqingCao
reviewed
Sep 29, 2025
MengqingCao
reviewed
Sep 29, 2025
Signed-off-by: wangli <[email protected]>
wangxiyuan
added a commit
that referenced
this pull request
Sep 29, 2025
### What this PR does / why we need it? This PR added the initial DeepSeek V3.2 support with [vLLM v0.11.0](https://github.com/vllm-project/vllm/tree/releases/v0.11.0) (not released yet). We will complete vLLM adaptation as soon as possible. This feature will be ready in recent 1-2 days. Related doc: #3223 . ### Does this PR introduce _any_ user-facing change? Yes! ### How was this patch tested? CI passed and Run deepseek doc soon. - vLLM version: v0.11.0rc3 - vLLM main: vllm-project/vllm@releases/v0.11.0 --------- Signed-off-by: wangxiyuan <[email protected]> Signed-off-by: zzzzwwjj <[email protected]> Signed-off-by: linfeng-yuan <[email protected]> Signed-off-by: wxsIcey <[email protected]> Signed-off-by: MengqingCao <[email protected]> Co-authored-by: zzzzwwjj <[email protected]> Co-authored-by: linfeng-yuan <[email protected]> Co-authored-by: wxsIcey <[email protected]> Co-authored-by: MengqingCao <[email protected]>
|
This pull request has conflicts, please resolve those before we can evaluate the pull request. |
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.
What this PR does / why we need it?
deepseek-v3.1-bf16multi-node mp backend tutorialdeepseek-v3.1-w8a8tp16 single node on a3 turorialDoes this PR introduce any user-facing change?
How was this patch tested?