hyperloom-remote-mn-qwen3-30b SKILL.md skillA
hyperloom-remote-mn-qwen3-30b from amd-agi/hyperloom is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add amd-agi/hyperloom/hyperloom-remote-mn-qwen3-30b@git:20260827.1988620Pins git:20260827.1988620 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- amd-agi/hyperloom
- Path
docs/how-to/multi-node/hyperloom-remote-mn-qwen3-30b/SKILL.md- Versions recorded
- 5
- Latest version
- git:20260827.1988620, committed Aug 27, 2026
- First version recorded
- Aug 2, 2026
- Size
- 7,319 bytes
- Repository stars
- 262
- License
- a license file GitHub does not identify
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.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Hyperloom Remote Multi-Node — Qwen3-30B-A3B
Pinned workload for a remote multi-node `optimize` run. Pick **one** backend
below and pass its `FLAGS` + `Environment` block to `inference_optimizer
optimize`; the agent launches it in the background and monitors `state.json`
until a terminal `stop_reason` — success (`target_reached`, `global_converged`,
`time_exhausted`, `max_ticks`) or early failure (`baseline_failed`,
`baseline_accuracy_failed`) that ends the run before optimizing. Concept and variable reference:
`@../../../reference/multi-node.md`. Optimizer skill: `@${HYPERLOOM_SKILL_PATH}`
(fallback `@../../../../src/hyperloom/inference_optimizer/SKILL.md`).
## Prerequisites
- **`NFS_SHARED_ROOT`**: cluster-wide shared mount at the **same absolute path**
on the sandbox and every GPU pod (model, tool checkouts, session artifacts).
Required; local-only paths break multi-node restart and benchmarks.
- **A provisioned cluster**: the platform creates the GPU pods and hands them
over via `HYPERLOOM_MN_EXT_*` (platform-injected; never passed on the CLI).
`optimize` adopts that cluster and exits 2 without it.
See `@../../../reference/multi-node.md`.
…Read the whole file at its exact version.
How to install
mdr add amd-agi/hyperloom/hyperloom-remote-mn-qwen3-30b@sha256:a02e366de1b63096The line at the top of this page pins the label git:20260827.1988620, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_5awfoekbdecpyqh7)
5 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Aug 2, 2026 and Aug 27, 2026, about one every 6 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260827.1988620 latest | 2026-08-27 | 1988620 | 7,319 B | A | view · diff |
| git:20260821.56fe7bb | 2026-08-21 | 56fe7bb | 7,308 B | A | view · diff |
| git:20260819.d10c098 | 2026-08-19 | d10c098 | 7,298 B | A | view · diff |
| git:20260803.be96432 | 2026-08-03 | be96432 | 7,276 B | A | view · diff |
| git:20260802.980063c | 2026-08-02 | 980063c | 7,234 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (7319 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
amd-agi/hyperloom · 262 stars · license a license file GitHub does not identify · pushed 2026-11-06 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_5awfoekbdecpyqh7 GET https://markdownregistry.com/api/v1/resolve?ref=amd-agi/hyperloom/hyperloom-remote-mn-qwen3-30b GET https://markdownregistry.com/api/v1/blob/a02e366de1b630963da47207ed32871df03c813e2617ea2fd2728bc7d3f1c92c
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.