Conversation
Add documentation for serving multiple models through a single gateway endpoint using BBR and Heimdall schedulers. The guide covers deploying Gateway, Body-Based Router, per-model Heimdall instances, and InferenceService resources with vllm-hf-hub-offline templates. Also reorder sidebar positions in the operations section. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Contributor
There was a problem hiding this comment.
Pull request overview
This PR adds a new operations guide for multi-model serving through a single gateway endpoint, using Body-Based Router (BBR) and Heimdall schedulers in the MoAI Inference Framework. It also reorders sidebar positions in the operations section.
Changes:
- Add
multi-model.mdxdocumenting full setup of multi-model routing with BBR, Heimdall, and InferenceService resources across GPU types - Reorder sidebar positions:
latest-releasemoved to-999,container-image-caching-with-harbormoved to30, new guide placed at20
Reviewed changes
Copilot reviewed 3 out of 3 changed files in this pull request and generated no comments.
| File | Description |
|---|---|
website/docs/operations/multi-model.mdx |
New guide covering architecture, gateway, BBR, Heimdall, InferenceService deployment, request examples, and cleanup for multi-model serving |
website/docs/operations/latest-release.mdx |
Sidebar position changed from 1 to -999 to pin it at the top |
website/docs/operations/container-image-caching-with-harbor/index.mdx |
Sidebar position changed from 4 to 30 to accommodate new ordering |
You can also share your feedback on Copilot code review. Take the survey.
Member
Author
Code reviewNo issues found. Checked for bugs and CLAUDE.md compliance. 🤖 Generated with Claude Code |
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
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.
Summary
website/docs/operations/multi-model.mdxdocumenting how to serve multiple models through a single gateway endpoint using BBR and Heimdall schedulersgateway.bbr.models, and InferenceService resources usingvllm-hf-hub-offlinetemplatesTest plan
hyeonkinamespace) with Llama 3.2 1B and Qwen 3 1.7B on MI250X-Gateway-Model-Nameheader routing works without BBR🤖 Generated with Claude Code