Skip to content

Conversation

@zouyida2052
Copy link
Contributor

What this PR does / why we need it?

add mtp develop guide doc

Does this PR introduce any user-facing change?

no

How was this patch tested?

Signed-off-by: zouyida2052 <zouyida2002@gmail.com>
Signed-off-by: zouyida2052 <zouyida2002@gmail.com>
@github-actions
Copy link

github-actions bot commented Nov 3, 2025

👋 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.

@github-actions github-actions bot added the documentation Improvements or additions to documentation label Nov 3, 2025
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 adds a developer guide for Multi-Token Prediction (MTP). The documentation is well-structured and provides a good overview of the feature, its usage, and implementation details. I've found a minor but important typo in a command-line example that could cause issues for users. Correcting this will improve the quality of the documentation.

## How to Use MTP
To enable MTP for DeepSeek-V3 models, add the following parameter when starting the service:

`--speculative_config={"method": "deepseek_mtp", "num_speculative_tokens": 1}'`
Copy link
Contributor

Choose a reason for hiding this comment

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

high

There is a typo in the example command. A trailing single quote ' is present, which will cause a shell error if a user copy-pastes it. Please remove it to ensure the command is correct.

Suggested change
`--speculative_config={"method": "deepseek_mtp", "num_speculative_tokens": 1}'`
`--speculative_config={"method": "deepseek_mtp", "num_speculative_tokens": 1}`

Signed-off-by: zouyida2052 <zouyida2002@gmail.com>
@github-actions
Copy link

github-actions bot commented Nov 6, 2025

This pull request has conflicts, please resolve those before we can evaluate the pull request.

@wangxiyuan
Copy link
Collaborator

we'll cherry-pick docs from main in one PR later. Thanks.

@wangxiyuan wangxiyuan closed this Nov 10, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

documentation Improvements or additions to documentation merge-conflicts

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants