8000 [Build] feature: start the Mooncake master server through Docker by Chasing1020 · Pull Request #320 · kvcache-ai/Mooncake · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

[Build] feature: start the Mooncake master server through Docker #320

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
May 13, 2025

Conversation

Chasing1020
Copy link
Contributor

This pr has optimized the building process of the Dockerfile and fixed the potential issues in the original building method:

  1. In the original method of using wget https://github.com/kvcache-ai/Mooncake/archive/refs/heads/main.zip, after downloading and unzipping, the project will lack the .git file. As a result, during the bash dependencies.sh stage, the submodule cannot be found.
  2. The RUN commands have been combined and the cache has been deleted to reduce the size of the image.
  3. It is now allowed to directly start the mooncake_master_server through the container.

@Chasing1020
Copy link
Contributor Author
Chasing1020 commented May 6, 2025

Why add this expose line with these two ports?

@alogfans I have removed it

@stmatengss
Copy link
Collaborator

This Dockerfile should be general and simple as a base Dockerfile, so it can be reused to construct the mooncake environment.

@stmatengss
Copy link
Collaborator

Should we add a new CI for testing dockerfile?

Signed-off-by: Chasing1020 <chasing1020@gmail.com>
Signed-off-by: Chasing1020 <chasing1020@gmail.com>
Copy link
Contributor
@Copilot Copilot AI left a comment

Choose a reason for hiding this comment

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

Pull Request Overview

This PR optimizes the Docker build process for the Mooncake master server by changing the source retrieval method and improving image cleanup and size reduction.

  • Switches from downloading the source via wget/unzip to copying the entire context.
  • Combines RUN commands and adds cleanup steps to reduce image size.
  • Enables directly starting the mooncake_master_server from the container.
Comments suppressed due to low confidence (1)

Dockerfile:6

  • Ensure that the .git directory is included in the build context if dependencies.sh relies on submodules, as .dockerignore may exclude it.
COPY . .

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
@stmatengss stmatengss merged commit feb26e7 into kvcache-ai:main May 13, 2025
25 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants
0