hyperloom-qwen3-8b-3h SKILL.md skillB

hyperloom-qwen3-8b-3h from amd-agi/hyperloom is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add amd-agi/hyperloom/hyperloom-qwen3-8b-3h@git:20261106.2f99e29

Pins git:20261106.2f99e29 in mdr.lock. Pin the fingerprint instead.

Audit grade
B, 16 of 17 checks passed
Kind
SKILL.md skill
Repository
amd-agi/hyperloom
Path
examples/hyperloom-qwen3-8b-3h/SKILL.md
Versions recorded
22
Latest version
git:20261106.2f99e29, committed Nov 6, 2026
First version recorded
Aug 31, 2026
Size
12,517 bytes
Repository stars
262
License
a license file GitHub does not identify

Run a 3-hour Hyperloom Qwen3-8B FRAMEWORK_AGENT (OPTIMIZE) session without the Kernel Agent. Use when the user wants a short, framework-only Hyperloom demo on the local AMD ROCm environment.

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 Qwen3-8B 3h Framework-Only (No-Kernel) Run

Load `.env` with the preamble below and resolve `HYPERLOOM_SKILL_PATH`. Read and follow the optimizer skill at `@${HYPERLOOM_SKILL_PATH}` before launching. If `HYPERLOOM_SKILL_PATH` is missing, fall back to `@hyperloom/inference_optimizer/SKILL.md` (wheel install) or `@src/hyperloom/inference_optimizer/SKILL.md` (source checkout). This skill provides the concrete workload and launch constraints for a short Qwen3-8B demo.

## Execution Shell

Run this in the current Hyperloom workspace before setup or runtime installation.
Repeat it in each new execution shell, including inside Docker; the shared loader
fills dotenv gaps without replacing existing non-empty exports.

```bash
set -e
export REPO_ROOT="$(pwd -P)"
INSTALL_SH="${REPO_ROOT}/hyperloom/inference_optimizer/assets/install.sh"
if [ ! -f "$INSTALL_SH" ]; then
  INSTALL_SH="${REPO_ROOT}/src/hyperloom/inference_optimizer/assets/install.sh"
fi
. "${INSTALL_SH%/*}/runtime_env.sh"
load_dotenv_no_clobber
```

## Run Mode

Resolve the run mode before launching Hyperloom:

1. If `HYPERLOOM_RUN_MODE=baremetal` or it is unset, run this demo directly on the host.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add amd-agi/hyperloom/hyperloom-qwen3-8b-3h@sha256:4a8c86ef6d882bc2

The line at the top of this page pins the label git:20261106.2f99e29, 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_t2o43pqafxwrc2fh.svg)](https://markdownregistry.com/a/art_t2o43pqafxwrc2fh)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 22 versions of this file, between Aug 31, 2026 and Nov 6, 2026, about one every 3 days.

versioncommittedcommitsizeaudit
git:20261106.2f99e29 latest2026-11-06 2f99e29 12,517 BB view · diff
git:20261103.a5836c92026-11-03 a5836c9 12,546 BB view · diff
git:20261026.32e80a92026-10-26 32e80a9 12,546 BB view · diff
git:20261012.b22d13b2026-10-12 b22d13b 12,546 BB view · diff
git:20261009.82e4b512026-10-09 82e4b51 12,394 BB view · diff
git:20261009.976d7a02026-10-09 976d7a0 12,394 BB view · diff
git:20260927.737d1e12026-09-27 737d1e1 12,503 BB view · diff
git:20260927.59d8f7f2026-09-27 59d8f7f 12,484 BB view · diff
git:20260923.db3cc152026-09-23 db3cc15 11,504 BB view · diff
git:20260923.44d87312026-09-23 44d8731 11,487 BB view · diff
git:20260921.b8761292026-09-21 b876129 11,450 BB view · diff
git:20260917.20798772026-09-17 2079877 11,452 BB view · diff
git:20260917.0d8dd3b2026-09-17 0d8dd3b 10,979 BB view · diff
git:20260917.55ed8832026-09-17 55ed883 11,090 BB view · diff
git:20260916.562a7ce2026-09-16 562a7ce 11,056 BB view · diff
git:20260915.97eadf52026-09-15 97eadf5 10,698 BB view · diff
git:20260914.f052bba2026-09-14 f052bba 10,698 BB view · diff
git:20260909.0a8edb12026-09-09 0a8edb1 10,698 BB view · diff
git:20260901.97ae03d2026-09-01 97ae03d 10,542 BB view · diff
git:20260831.aeb13432026-08-31 aeb1343 10,647 BB view · diff
git:20260831.6248b662026-08-31 6248b66 13,036 BB view · diff
git:20260831.975bd942026-08-31 975bd94 12,596 BB view

Audit of the latest version

B  16 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • fail: No instruction to read or print local credentials (matched: Read `HYPERLOOM_DOCKER_TARGET_HOST` from `.env)
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (12517 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 base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.

Source

GitHub

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_t2o43pqafxwrc2fh
GET https://markdownregistry.com/api/v1/resolve?ref=amd-agi/hyperloom/hyperloom-qwen3-8b-3h
GET https://markdownregistry.com/api/v1/blob/4a8c86ef6d882bc2429bedefa56e518eb68b5c209c3e506d102661db9dc738e4

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.

More from amd-agi/hyperloom

analyze-upstream-pr SKILL.md skill
amd-agi/hyperloom · .claude/skills/analyze-upstream-pr/SKILL.md · Analyze whether an upstream pull request applies to an AMD/ROCm deployment. Invoke with the PR's repository and number…
git:20261020.6cc6611 · audit A · 262 stars
check-prior-art SKILL.md skill
amd-agi/hyperloom · .claude/skills/check-prior-art/SKILL.md · Check whether a planned optimization already exists upstream before building it. Invoke with a one-sentence mechanism…
git:20261020.a160c20 · audit A · 262 stars
review-pr SKILL.md 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:20261029.8d68eef · audit A · 262 stars
AGENTS.md AGENTS.md file
amd-agi/hyperloom · AGENTS.md
git:20261030.f418170 · audit A · 262 stars
CLAUDE.md CLAUDE.md file
amd-agi/hyperloom · CLAUDE.md
git:20260921.6b4b413 · audit B · 262 stars
hyperloom-remote-mn-qwen3-30b SKILL.md 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 · 262 stars
hyperloom-custom-advanced SKILL.md 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:20261106.2f99e29 · audit B · 262 stars
hyperloom-qwen3-14b-fp8-12h-forge SKILL.md skill
amd-agi/hyperloom · examples/hyperloom-qwen3-14b-fp8-12h-forge/SKILL.md · Run a 12-hour Hyperloom Qwen3-14B-FP8 optimization session on SGLang, vLLM or ATOM with the per-kernel KernelForge…
git:20261106.2f99e29 · audit B · 262 stars
hyperloom-qwen3-14b-fp8-12h SKILL.md skill
amd-agi/hyperloom · examples/hyperloom-qwen3-14b-fp8-12h/SKILL.md · Run a 12-hour Hyperloom Qwen3-14B-FP8 optimization session on SGLang, vLLM or ATOM. Use when the user wants a…
git:20261106.2f99e29 · audit B · 262 stars
hyperloom-workload-optimizer SKILL.md skill
amd-agi/hyperloom · examples/skills/hyperloom-workload-optimizer/SKILL.md · Autonomously optimizes end-to-end LLM inference throughput on AMD Instinct GPUs and reports a validated gain, using the…
git:20260924.f2e2a9c · audit A · 262 stars
critic-agent SKILL.md 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:20261023.0718479 · audit A · 262 stars
quantization-agent SKILL.md 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:20261029.20d8b20 · audit A · 262 stars

Every file in amd-agi/hyperloom

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