inference_optimizer SKILL.md skillB

inference_optimizer 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/inference_optimizer@git:20261106.d2194d1

Pins git:20261106.d2194d1 in mdr.lock. Pin the fingerprint instead.

Audit grade
B, 16 of 17 checks passed
Kind
SKILL.md skill
Repository
amd-agi/hyperloom
Path
src/hyperloom/inference_optimizer/SKILL.md
Versions recorded
68
Latest version
git:20261106.d2194d1, committed Nov 6, 2026
First version recorded
Sep 3, 2026
Size
104,210 bytes
Repository stars
262
License
a license file GitHub does not identify

Launches and monitors Hyperloom's multi-agent inference optimizer for LLM serving on AMD GPUs. Use when the user asks to optimize an inference model, run Magpie benchmarks/profiles, resume an inference_optimizer session, tune SGLang/vLLM serving parameters, run TraceLens/kernel-agent, or validate end-to-end throughput gains in a new inference 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

# Inference Optimizer Skill

You are the launcher and monitor. The optimizer itself is the Python
`inference_optimizer` runtime under this repository. Do not manually optimize
inside chat unless debugging; launch the CLI, poll persisted state, and report
objective progress.

## What This Skill Runs

The CLI starts a Python Coordinator that coordinates:

- Orchestration: decides next actions (`baseline`, `explore`, `specialist`, `integrate_patch`, `sweep`, Kernel requests). In CLOSE, the Coordinator auto-enqueues `report` at session end; Orchestration may also propose it.
- Kernel (programmatic, not LLM): the Coordinator dispatches `trace_analyze`, `integrate`, and related request kinds directly to Python handlers without an LLM turn. The `run_gemm_tuning` and `run_fusion` lanes are Coordinator-owned: they run inside the `kernel_agent` task at KERNEL entry and PolicyGate rejects an agent request for either.
- Critic: proposal review (default `--critic-agent`; see
  [Critic Backend Selection](#critic-backend-selection) for modes).

State lives under a **session directory** (per optimization run).
The **workspace root** is ``$USER_DATA_PATH`` (default
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add amd-agi/hyperloom/inference_optimizer@sha256:63c01deb4d4e157d

The line at the top of this page pins the label git:20261106.d2194d1, 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_y3pwsnfmpk5l2hc5.svg)](https://markdownregistry.com/a/art_y3pwsnfmpk5l2hc5)

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

Versions

The registry has recorded 68 versions of this file, between Sep 3, 2026 and Nov 6, 2026, more than one a day.

versioncommittedcommitsizeaudit
git:20261106.d2194d1 latest2026-11-06 d2194d1 104,210 BB view · diff
git:20261106.bb168fc2026-11-06 bb168fc 103,501 BB view · diff
git:20261104.50c166c2026-11-04 50c166c 103,390 BB view · diff
git:20261102.a026a2e2026-11-02 a026a2e 102,862 BB view · diff
git:20261102.206c3e92026-11-02 206c3e9 102,696 BB view · diff
git:20261030.711fb6e2026-10-30 711fb6e 102,195 BB view · diff
git:20261029.c9b2d432026-10-29 c9b2d43 101,350 BB view · diff
git:20261029.700ad312026-10-29 700ad31 101,147 BB view · diff
git:20261028.6d9079a2026-10-28 6d9079a 101,171 BB view · diff
git:20261027.c3af9562026-10-27 c3af956 101,125 BB view · diff
git:20261027.79cc8762026-10-27 79cc876 100,820 BB view · diff
git:20261023.7e98e1f2026-10-23 7e98e1f 99,204 BB view · diff
git:20261023.5c333152026-10-23 5c33315 98,344 BB view · diff
git:20261023.1a5bcbf2026-10-23 1a5bcbf 98,352 BB view · diff
git:20261023.f64e36e2026-10-23 f64e36e 98,045 BB view · diff
git:20261023.e99ec912026-10-23 e99ec91 97,951 BB view · diff
git:20261022.9c42fdf2026-10-22 9c42fdf 97,651 BB view · diff
git:20261022.5a7523f2026-10-22 5a7523f 97,683 BB view · diff
git:20261021.fbcd0c32026-10-21 fbcd0c3 97,391 BB view · diff
git:20261021.9da87882026-10-21 9da8788 97,171 BB view · diff
git:20261021.cf92d632026-10-21 cf92d63 96,926 BB view · diff
git:20261017.75df5512026-10-17 75df551 96,773 BB view · diff
git:20261017.9845e912026-10-17 9845e91 96,162 BB view · diff
git:20261016.114a40b2026-10-16 114a40b 96,150 BB view · diff
git:20261016.8f3e2ad2026-10-16 8f3e2ad 95,808 BB view · diff
git:20261016.cd9eebb2026-10-16 cd9eebb 95,769 BB view · diff
git:20261015.9f3e6852026-10-15 9f3e685 95,049 BB view · diff
git:20261014.40feefc2026-10-14 40feefc 94,234 BB view · diff
git:20261014.d393b5b2026-10-14 d393b5b 92,955 BB view · diff
git:20261013.fb7de832026-10-13 fb7de83 92,319 BB view · diff
git:20261013.059c1462026-10-13 059c146 93,202 BB view · diff
git:20261013.2086a862026-10-13 2086a86 92,592 BB view · diff
git:20261013.6df52ff2026-10-13 6df52ff 92,544 BB view · diff
git:20261011.7b518de2026-10-11 7b518de 92,751 BB view · diff
git:20261009.87bf19e2026-10-09 87bf19e 91,590 BB view · diff
git:20261009.976d7a02026-10-09 976d7a0 91,614 BB view · diff
git:20261008.1a9ce492026-10-08 1a9ce49 92,118 BB view · diff
git:20261007.f2b32cd2026-10-07 f2b32cd 92,034 BB view · diff
git:20261006.26557fd2026-10-06 26557fd 92,236 BB view · diff
git:20261006.ba23ca92026-10-06 ba23ca9 91,735 BB view · diff
git:20261006.bd5e9fa2026-10-06 bd5e9fa 91,755 BB view · diff
git:20261006.d8837c32026-10-06 d8837c3 91,793 BB view · diff
git:20260930.03b18ff2026-09-30 03b18ff 86,463 BB view · diff
git:20260930.473121d2026-09-30 473121d 86,348 BB view · diff
git:20260930.852bb792026-09-30 852bb79 85,920 BB view · diff
git:20260927.737d1e12026-09-27 737d1e1 85,766 BB view · diff
git:20260927.59d8f7f2026-09-27 59d8f7f 85,747 BB view · diff
git:20260924.afb1fa52026-09-24 afb1fa5 84,938 BB view · diff
git:20260924.fab4afc2026-09-24 fab4afc 84,599 BB view · diff
git:20260924.40845ef2026-09-24 40845ef 84,628 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 recursive delete of root, home or parent (matched: rm -rf ~/)
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (104210 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 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

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_y3pwsnfmpk5l2hc5
GET https://markdownregistry.com/api/v1/resolve?ref=amd-agi/hyperloom/inference_optimizer
GET https://markdownregistry.com/api/v1/blob/63c01deb4d4e157d790e5482fb418bfc4317768299251b03aa59cdea99a36136

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-qwen3-8b-3h SKILL.md 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: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

Every file in amd-agi/hyperloom

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