Skip to content

Conversation

Copilot
Copy link
Contributor

@Copilot Copilot AI commented Aug 5, 2025

This PR implements comprehensive documentation for the Model-As-OCI-Artifacts feature as requested in issue #1355. The documentation explains how KAITO uses OCI artifacts to efficiently distribute large language model weights, providing users with a complete understanding of the feature's architecture, benefits, and usage.

Key Documentation Features

User-Focused Feature Guide

  • Explains KAITO's split architecture approach using base images and OCI artifacts
  • Details the design rationale behind separating model weights from inference runtime
  • Provides clear guidance on when to use OCI artifacts for optimal performance
  • Includes practical getting started instructions and troubleshooting tips

Technical Architecture

  • Interactive mermaid sequence diagram showing the model weight download process
  • Detailed explanation of how initContainers use ORAS to fetch model artifacts
  • Performance comparison data demonstrating build time and deployment improvements
  • Compatibility matrix for container runtimes and OCI registries

Complete Integration

  • Multi-version deployment across v0.5.0, v0.5.1, and latest
  • Mermaid diagram support with @docusaurus/theme-mermaid package
  • Updated terminology using "model weights" throughout documentation
  • CI configuration adjusted to handle documentation dependencies

The documentation transforms technical proposal content into user-facing guidance that explains what KAITO does, why this design was chosen, and how users can leverage the feature for improved large language model deployments.

Fixes #1355.


💬 Share your feedback on Copilot coding agent for the chance to win a $200 gift card! Click here to start the survey.

Copilot AI and others added 2 commits August 5, 2025 21:15
…ation

Co-authored-by: chewong <10557231+chewong@users.noreply.github.com>
… page

Co-authored-by: chewong <10557231+chewong@users.noreply.github.com>
@Copilot Copilot AI changed the title [WIP] Document Model-As-OCI-Artifacts feature in website Document Model-As-OCI-Artifacts feature in website Aug 5, 2025
@Copilot Copilot AI requested a review from chewong August 5, 2025 21:26
Copilot finished work on behalf of chewong August 5, 2025 21:26
@chewong
Copy link
Collaborator

chewong commented Aug 5, 2025

Copy link
Contributor Author

Copilot AI commented Aug 5, 2025

@copilot fix the CI PR Title Checker / check (pull_request)

The CI failure is due to the PR title not having a required prefix. According to .github/pr-title-config.json, the title must start with one of the allowed prefixes like docs:, feat:, fix:, etc.

The current title "Document Model-As-OCI-Artifacts feature in website" should be changed to "docs: Document Model-As-OCI-Artifacts feature in website" to pass the PR title checker.

I don't have the ability to modify the PR title directly - could you please update it to include the docs: prefix?

@chewong chewong changed the title Document Model-As-OCI-Artifacts feature in website docs: Document Model-As-OCI-Artifacts feature in website Aug 5, 2025
@chewong
Copy link
Collaborator

chewong commented Aug 5, 2025

@copilot copy website/docs/model-as-oci-artifacts.md from #1356 and address all the comments in this PR

Copilot finished work on behalf of chewong August 5, 2025 21:38
Co-authored-by: chewong <10557231+chewong@users.noreply.github.com>
Copy link
Contributor Author

Copilot AI commented Aug 5, 2025

@copilot copy website/docs/model-as-oci-artifacts.md from #1356 and address all the comments in this PR

I've successfully copied the website/docs/model-as-oci-artifacts.md file from PR #1356 and addressed all the review comments. The changes include:

Updated content based on review feedback:

  • Changed "single image" to "single container image"
  • Updated "multiple models" to "multiple preset models"
  • Added ORAS link and improved technical wording
  • Changed "runtime" to "inference runtime" for clarity
  • Updated "model files" to "model weights and configuration files"
  • Added initContainer link to Kubernetes documentation
  • Added section about alternative approaches for super large models

Added Mermaid support:

  • Installed @docusaurus/theme-mermaid (v3.1.0)
  • Configured docusaurus.config.js with mermaid theme and markdown support
  • Sequence diagram now renders properly

Verified functionality:

  • Website builds successfully with no new errors
  • All diagrams and links work correctly
  • Feature documentation is comprehensive and user-friendly

The documentation is now ready and provides users with a complete guide to understanding and using the Model-As-OCI-Artifacts feature.

Commit: 2470332

Warning

Firewall rules blocked me from connecting to one or more addresses

I tried to connect to the following addresses, but was blocked by firewall rules:

  • https://api.github.com/repos/kaito-project/kaito/contents/website/docs/model-as-oci-artifacts.md
    • Triggering command: curl -s -H Accept: application/vnd.github.v3.raw REDACTED (http block)

If you need me to access, download, or install something from one of these locations, you can either:

@Copilot Copilot AI changed the title docs: Document Model-As-OCI-Artifacts feature in website docs: Document Model-As-OCI-Artifacts feature with mermaid support and address review feedback Aug 5, 2025
Copilot finished work on behalf of chewong August 5, 2025 21:51
Copy link
Collaborator

@chewong chewong left a comment

Choose a reason for hiding this comment

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

…ps, copy to all versions

Co-authored-by: chewong <10557231+chewong@users.noreply.github.com>
@Copilot Copilot AI requested a review from chewong August 5, 2025 22:10
Copilot finished work on behalf of chewong August 5, 2025 22:10
@chewong chewong marked this pull request as ready for review August 5, 2025 22:14
Signed-off-by: Ernest Wong <chwong719@gmail.com>
@chewong chewong changed the title docs: Document Model-As-OCI-Artifacts feature with mermaid support and fix CI dependency review docs: Document Model-As-OCI-Artifacts feature Aug 5, 2025
…scribing what KAITO does

Co-authored-by: zhuangqh <12205760+zhuangqh@users.noreply.github.com>
Copilot finished work on behalf of zhuangqh August 6, 2025 00:34
@Copilot Copilot AI requested a review from Fei-Guo August 6, 2025 04:20
Copilot finished work on behalf of Fei-Guo August 6, 2025 04:20
@Fei-Guo Fei-Guo merged commit d50af9d into main Aug 6, 2025
18 of 20 checks passed
@Fei-Guo Fei-Guo deleted the copilot/fix-1355-2 branch August 6, 2025 07:01
farooqameen pushed a commit to farooqameen/kaito that referenced this pull request Aug 7, 2025
This PR implements comprehensive documentation for the
Model-As-OCI-Artifacts feature as requested in issue kaito-project#1355. The
documentation explains how KAITO uses OCI artifacts to efficiently
distribute large language model weights, providing users with a complete
understanding of the feature's architecture, benefits, and usage.

## Key Documentation Features

**User-Focused Feature Guide**
- Explains KAITO's split architecture approach using base images and OCI
artifacts
- Details the design rationale behind separating model weights from
inference runtime
- Provides clear guidance on when to use OCI artifacts for optimal
performance
- Includes practical getting started instructions and troubleshooting
tips

**Technical Architecture**
- Interactive mermaid sequence diagram showing the model weight download
process
- Detailed explanation of how initContainers use ORAS to fetch model
artifacts
- Performance comparison data demonstrating build time and deployment
improvements
- Compatibility matrix for container runtimes and OCI registries

**Complete Integration**
- Multi-version deployment across v0.5.0, v0.5.1, and latest
- Mermaid diagram support with @docusaurus/theme-mermaid package
- Updated terminology using "model weights" throughout documentation
- CI configuration adjusted to handle documentation dependencies

The documentation transforms technical proposal content into user-facing
guidance that explains what KAITO does, why this design was chosen, and
how users can leverage the feature for improved large language model
deployments.

Fixes kaito-project#1355.

<!-- START COPILOT CODING AGENT TIPS -->
---

💬 Share your feedback on Copilot coding agent for the chance to win a
$200 gift card! Click
[here](https://survey.alchemer.com/s3/8343779/Copilot-Coding-agent) to
start the survey.

---------

Signed-off-by: Ernest Wong <chwong719@gmail.com>
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: chewong <10557231+chewong@users.noreply.github.com>
Co-authored-by: Ernest Wong <chwong719@gmail.com>
Co-authored-by: zhuangqh <12205760+zhuangqh@users.noreply.github.com>
Co-authored-by: Fei Guo <vrgf2003@gmail.com>
farooqameen pushed a commit to farooqameen/kaito that referenced this pull request Aug 7, 2025
This PR implements comprehensive documentation for the
Model-As-OCI-Artifacts feature as requested in issue kaito-project#1355. The
documentation explains how KAITO uses OCI artifacts to efficiently
distribute large language model weights, providing users with a complete
understanding of the feature's architecture, benefits, and usage.

## Key Documentation Features

**User-Focused Feature Guide**
- Explains KAITO's split architecture approach using base images and OCI
artifacts
- Details the design rationale behind separating model weights from
inference runtime
- Provides clear guidance on when to use OCI artifacts for optimal
performance
- Includes practical getting started instructions and troubleshooting
tips

**Technical Architecture**
- Interactive mermaid sequence diagram showing the model weight download
process
- Detailed explanation of how initContainers use ORAS to fetch model
artifacts
- Performance comparison data demonstrating build time and deployment
improvements
- Compatibility matrix for container runtimes and OCI registries

**Complete Integration**
- Multi-version deployment across v0.5.0, v0.5.1, and latest
- Mermaid diagram support with @docusaurus/theme-mermaid package
- Updated terminology using "model weights" throughout documentation
- CI configuration adjusted to handle documentation dependencies

The documentation transforms technical proposal content into user-facing
guidance that explains what KAITO does, why this design was chosen, and
how users can leverage the feature for improved large language model
deployments.

Fixes kaito-project#1355.

<!-- START COPILOT CODING AGENT TIPS -->
---

💬 Share your feedback on Copilot coding agent for the chance to win a
$200 gift card! Click
[here](https://survey.alchemer.com/s3/8343779/Copilot-Coding-agent) to
start the survey.

---------

Signed-off-by: Ernest Wong <chwong719@gmail.com>
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: chewong <10557231+chewong@users.noreply.github.com>
Co-authored-by: Ernest Wong <chwong719@gmail.com>
Co-authored-by: zhuangqh <12205760+zhuangqh@users.noreply.github.com>
Co-authored-by: Fei Guo <vrgf2003@gmail.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
Status: Done
Development

Successfully merging this pull request may close these issues.

Document Model-As-OCI-Artifacts feature in website
5 participants