guide-odin
OfficialExpert Odin guide for MoAI inference.
Software Engineering#kubernetes#presets#parallelism#odin#inference-service#template-merge#leaderworkerset
Authormoreh-dev
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Odin orchestrates and reconciles InferenceService workloads in Kubernetes, enabling scalable, repeatable deployment of AI inference workloads via a reusable, template-driven configuration system.
Core Features & Use Cases
- Template composition with InferenceServiceTemplate to layer runtime-bases and presets, enabling clean separation of platform and model configurations.
- Support for multiple parallelism styles (tensor, pipeline, data, expert) and workload types (Deployment or LeaderWorkerSet) to fit varied model and hardware layouts.
- End-to-end deployment patterns for vLLM-based serving, multi-node setups, and PD-disaggregation workflows, with rollback and rollout controls.
Quick Start
Run Odin in your cluster to deploy your first InferenceService using the vLLM presets and templates.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: guide-odin Download link: https://github.com/moreh-dev/mif/archive/main.zip#guide-odin Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.