exo-distributed
OfficialRun distributed LLMs on Apple Silicon with ease.
Authorplurigrid
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill enables distributed LLM inference across Apple Silicon devices with auto peer discovery, low-latency RDMA, and native MLX acceleration, removing the complexity of manual cluster setup.
Core Features & Use Cases
- Auto Peer Discovery: Devices join a cluster automatically as they come online.
- RDMA over Thunderbolt 5: Low-latency cross-device communication.
- Model Sharding & Parallelism: Pipeline and tensor parallelism to scale large models.
- OpenAI-compatible API: Serve distributed inference via a familiar API for apps.
Quick Start
Install exo, start on the first device to elect master, then start on additional devices; the cluster forms and serves at http://localhost:8080 by default.
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: exo-distributed Download link: https://github.com/plurigrid/asi/archive/main.zip#exo-distributed Please download this .zip file, extract it, and install it in the .claude/skills/ directory.