Skip to content

Conversation

@atchernych
Copy link
Contributor

@atchernych atchernych commented Jul 17, 2025

Overview:

Create a guide for writing dynamo deployments CR

Details:

Where should the reviewer start?

Related Issues: (use one of the action keywords Closes / Fixes / Resolves / Relates to)

Summary by CodeRabbit

  • Documentation
    • Added a new guide explaining how to create and customize Kubernetes deployment files for serving models with the Dynamo framework, including example YAML snippets and configuration tips for different deployment patterns and backend architectures.

@coderabbitai
Copy link
Contributor

coderabbitai bot commented Jul 17, 2025

Walkthrough

A new documentation guide, create_deployment.md, has been added to explain how to create and customize Kubernetes deployment files for serving models using the Dynamo framework. The guide covers architecture selection, template customization, and key configuration points, including example YAML snippets and references to related deployment documentation.

Changes

File(s) Change Summary
docs/guides/dynamo_deploy/create_deployment.md Added a comprehensive guide on creating and customizing Kubernetes deployment files for Dynamo.

Sequence Diagram(s)

sequenceDiagram
    User->>Guide: Reads deployment guide
    Guide->>User: Explains architecture patterns
    User->>Guide: Selects deployment template
    Guide->>User: Shows customization options (YAML, commands, resources)
    User->>Kubernetes: Applies customized deployment YAML
    Kubernetes->>Dynamo: Deploys model serving components
Loading

Possibly related PRs

Poem

🐇
In YAML fields and clusters bright,
A guide appears to shed new light.
Choose your path—agg or disagg—
Tune your pods, let models brag!
With Dynamo’s docs, deploy with cheer,
Your serving dreams are drawing near.


Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share
🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

  • Review comments: Directly reply to a review comment made by CodeRabbit. Example:
    • I pushed a fix in commit <commit_id>, please review it.
    • Explain this complex logic.
    • Open a follow-up GitHub issue for this discussion.
  • Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
    • @coderabbitai explain this code block.
    • @coderabbitai modularize this function.
  • PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
    • @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
    • @coderabbitai read src/utils.ts and explain its main purpose.
    • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
    • @coderabbitai help me debug CodeRabbit configuration file.

Support

Need help? Create a ticket on our support page for assistance with any issues or questions.

Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.

CodeRabbit Commands (Invoked using PR comments)

  • @coderabbitai pause to pause the reviews on a PR.
  • @coderabbitai resume to resume the paused reviews.
  • @coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
  • @coderabbitai full review to do a full review from scratch and review all the files again.
  • @coderabbitai summary to regenerate the summary of the PR.
  • @coderabbitai generate sequence diagram to generate a sequence diagram of the changes in this PR.
  • @coderabbitai resolve resolve all the CodeRabbit review comments.
  • @coderabbitai configuration to show the current CodeRabbit configuration for the repository.
  • @coderabbitai help to get help.

Other keywords and placeholders

  • Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
  • Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
  • Add @coderabbitai anywhere in the PR title to generate the title automatically.

Documentation and Community

  • Visit our Documentation for detailed information on how to use CodeRabbit.
  • Join our Discord Community to get help, request features, and share feedback.
  • Follow us on X/Twitter for updates and announcements.

Copy link
Contributor

@coderabbitai coderabbitai bot left a comment

Choose a reason for hiding this comment

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

Actionable comments posted: 0

🧹 Nitpick comments (4)
docs/guides/dynamo_deploy/create_deployment.md (4)

3-4: Capitalize “Kubernetes” and “YAML” for consistency

Throughout the project documentation we capitalize proper nouns and abbreviations.

- The corresponding yaml files ... create a kubernetes deployment
+ The corresponding YAML files ... create a Kubernetes deployment

28-36: Minor grammar tweak & pluralize “roles”

The sentence reads more naturally in the present tense, and the list that follows describes multiple roles.

-The Frontend serves as a framework-agnostic HTTP entry point and is likely not to need many changes.
-It serves the following role:
+The Frontend is a framework-agnostic HTTP entry point and usually needs few changes.
+It serves the following roles:

31-46: Indent sub-bullets so Markdown renders them as part of the numbered list

Without indentation, Markdown engines will render each line as a new top-level list item rather than details of item 1/2/3.

Example fix for block starting at line 31:

-1. OpenAI-Compatible HTTP Server
-Provides `/v1/chat/completions` endpoint
-Handles HTTP request/response formatting
+1. OpenAI-Compatible HTTP Server  
+   • Provides `/v1/chat/completions` endpoint  
+   • Handles HTTP request/response formatting  

(Repeat for the other two sections.)


88-90: Fix stray back-tick and unify command spelling (dynamo-run)

-Each worker will launch `dynamo-run in=dyn//name out=sglang <model>`command
+Each worker launches `dynamo-run in=dyn//name out=sglang <model>` command

Also ensure the earlier example uses the same dynamo-run spelling for consistency.

📜 Review details

Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 2b29a0a and ed43be2.

📒 Files selected for processing (1)
  • docs/guides/dynamo_deploy/create_deployment.md (1 hunks)
🔇 Additional comments (1)
docs/guides/dynamo_deploy/create_deployment.md (1)

65-83: GPU resource key is not standard Kubernetes; clarify or correct

gpu: "1" will not be scheduled by vanilla Kubernetes. Most clusters expose GPUs under nvidia.com/gpu (or another vendor-specific resource name). If gpu is a Dynamo-specific abstraction, mention it explicitly; otherwise consider:

-          gpu: "1"
+          nvidia.com/gpu: "1"   # adjust to your cluster’s GPU resource name

@rmccorm4 rmccorm4 changed the title Create a guide for writing dynamo deployments CR docs: Create a guide for writing dynamo deployments CR Jul 17, 2025
@github-actions github-actions bot added the docs label Jul 17, 2025
@atchernych atchernych merged commit 3094278 into main Jul 24, 2025
13 of 15 checks passed
@atchernych atchernych deleted the DYN-722-yaml-readme branch July 24, 2025 21:17
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants