Home / amd-agi / hyperloom · examples/skills/hyperloom-workload-optimizer/SKILL.md · GitHub

hyperloom-workload-optimizer skillA

hyperloom-workload-optimizer is agent-read markdown (skill) from amd-agi/hyperloom: Autonomously optimizes end-to-end LLM inference throughput on AMD Instinct GPUs and reports a validated gain, using the Hyperloom multi-agent optimizer. Given a model, framework, workload (TP/EP, concurrency, ISL/OSL, precision), an objective and a time budget, it explores per-workload which levers to pull (serving/config parameters and env, framework enablement and source patches, and hot GPU-kernel rewrites), benchmarks each candidate, and returns the optimization stack that produced the gain..

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

<!--
Copyright (c) 2026 Advanced Micro Devices, Inc. All rights reserved.

See LICENSE for license information.
-->

# Hyperloom Workload Optimizer

You are the entry point for Hyperloom optimization on AMD Instinct GPUs. Your job
is the bootstrap: confirm the workspace, install the Hyperloom wheel, run
`/hyperloom-setup`, then hand the run to the skill that owns it.

The wheel installs the skills that own everything after setup: `hyperloom-setup`
for credentials and run mode, the demo skills for a workload preset, and
`inference_optimizer` for the launcher gates and monitoring. They ship with the
runtime, so they always match the installed version.

This is the agent-facing form of the human quickstart in
[examples/README.md](../../README.md).

## Out of scope for this skill

- Do not run `python -m hyperloom.inference_optimizer.cli optimize` yourself.
- Do not implement a GPU preflight, launcher gate, or background launch here. The
  installed skills own those, including the Iron Rules and the resume path.
- Do not ask for workload values (model, TP/EP, concurrency, ISL/OSL, precision,
  objective, budget) while installing or while setup is running. They belong to
…

Read the whole file at its exact version.

How to install

Latest version
mdr add amd-agi/hyperloom/hyperloom-workload-optimizer@git:20260921.1213b1b
Exact content
mdr add amd-agi/hyperloom/hyperloom-workload-optimizer@sha256:5d9c6e74514c37ab

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_vpjtx3gdhdggbkf7.svg)](https://markdownregistry.com/a/art_vpjtx3gdhdggbkf7)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260921.1213b1b latest2026-09-21 1213b1b 6,862 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (6862 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

GitHub

amd-agi/hyperloom · 199 stars · license NOASSERTION · pushed 2026-09-24 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_vpjtx3gdhdggbkf7
GET https://markdownregistry.com/api/v1/resolve?ref=amd-agi/hyperloom/hyperloom-workload-optimizer
GET https://markdownregistry.com/api/v1/blob/5d9c6e74514c37ab56968b902fa9dce7db2b2c88049f4d2759b86b69e281b313

Your agent 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.

More from amd-agi/hyperloom

review-pr skill
amd-agi/hyperloom · .claude/skills/review-pr/SKILL.md · Review a Hyperloom pull request. Invoke with a PR number whenever asked to review, re-review, or sanity-check a PR in…
git:20260922.f6a17b3 · audit A · 199 stars
AGENTS.md agents
amd-agi/hyperloom · AGENTS.md
git:20260921.e27c6de · audit A · 199 stars
CLAUDE.md claude
amd-agi/hyperloom · CLAUDE.md
git:20260921.6b4b413 · audit B · 199 stars
hyperloom-remote-mn-qwen3-30b skill
amd-agi/hyperloom · docs/how-to/multi-node/hyperloom-remote-mn-qwen3-30b/SKILL.md · Run a 4-hour multi-node Hyperloom Qwen3-30B-A3B optimization (Infera PD-disaggregated or RayJob aggregated) with…
git:20260827.1988620 · audit A · 199 stars
hyperloom-custom-advanced skill
amd-agi/hyperloom · examples/hyperloom-custom-advanced/SKILL.md · Run an advanced configurable Hyperloom optimization session with explicit model, framework, workload, objective, and…
git:20260923.44d8731 · audit B · 199 stars
hyperloom-qwen3-14b-fp8-12h-atom skill
amd-agi/hyperloom · examples/hyperloom-qwen3-14b-fp8-12h-atom/SKILL.md · Run a 12-hour Hyperloom Qwen3-14B-FP8 optimization session on the ATOM serving framework with the per-kernel…
git:20260918.2e45aad · audit B · 199 stars
hyperloom-qwen3-14b-fp8-12h-forge skill
amd-agi/hyperloom · examples/hyperloom-qwen3-14b-fp8-12h-forge/SKILL.md · Run a 12-hour Hyperloom Qwen3-14B-FP8 optimization session with the per-kernel KernelForge backend instead of GEAK. Use…
git:20260923.44d8731 · audit B · 199 stars
hyperloom-qwen3-14b-fp8-12h skill
amd-agi/hyperloom · examples/hyperloom-qwen3-14b-fp8-12h/SKILL.md · Run a 12-hour Hyperloom Qwen3-14B-FP8 optimization session. Use when the user wants a medium-length Hyperloom demo on…
git:20260923.44d8731 · audit B · 199 stars
hyperloom-qwen3-8b-3h skill
amd-agi/hyperloom · examples/hyperloom-qwen3-8b-3h/SKILL.md · Run a 3-hour Hyperloom Qwen3-8B FRAMEWORK_AGENT (OPTIMIZE) session without the Kernel Agent. Use when the user wants a…
git:20260923.44d8731 · audit B · 199 stars
critic-agent skill
amd-agi/hyperloom · src/hyperloom/agents/critic/SKILL.md · Critic layer for the inference optimizer. Use when Conductor asks for a Critic Review verdict on Orchestration or…
git:20260917.0d8dd3b · audit A · 199 stars
framework skill
amd-agi/hyperloom · src/hyperloom/agents/framework/SKILL.md
git:20260916.a3612d8 · audit C · 199 stars
quantization-agent skill
amd-agi/hyperloom · src/hyperloom/agents/quantization/SKILL.md · Hyperloom sub-agent that drives the AMD Quark PTQ skill chain end-to-end from a natural-language prompt. Produces a…
git:20260904.a64d24c · audit A · 199 stars

Every file in amd-agi/hyperloom

Browse by kind, by grade A, or by owner.