Hyperloom Remote Mn Qwen3 30b

Run a 4-hour multi-node Hyperloom Qwen3-30B-A3B optimization (Infera PD-disaggregated or RayJob aggregated) with --nodes 2 and sglang MoE tuning on MI325X. Hand this skill to the agent to launch and monitor the run.

AMD-AGI Updated
Hyperloom architecture

File contents

AMD-AGI/Hyperloom commit 967976c3d4

Frequently asked questions

npx get-skill add amd-agi/hyperloom-remote-mn-qwen3-30b