profiler SKILL.md skillA

profiler 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/profiler@git:20261105.0d95dc2

Pins git:20261105.0d95dc2 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
amd-agi/hyperloom
Path
src/hyperloom_arbor/.claude/skills/profiler/SKILL.md
Versions recorded
1
Latest version
git:20261105.0d95dc2, committed Nov 5, 2026
Size
5,913 bytes
Repository stars
262
License
a license file GitHub does not identify

Profile an LLM serving workload on ROCm to find where GPU time goes, with TraceLens on PyTorch-profiler traces of the served program. Start from the host's profile when there is one (in component mode, MB's TraceLens profile of the root); take a trace of your own only for what it does not cover, or after a KEEP moved the tree. Use when asked to profile, rank optimization sites, compare two trees' profiles, or write a dossier's profile (part 7) or kernel usage (part 8).

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

# Profiling on ROCm with TraceLens

Audience: an agent (or a person) asked where a serving workload's GPU time goes and what to optimize.

TraceLens (AMD-AGI/TraceLens) reads a PyTorch-profiler trace into tables: GPU time by op and by kernel, the GPU
timeline (busy, idle, communication), collectives across ranks, and rooflines. It is installed with the environment
(`$TRACELENS_ROOT`; its commands are on `PATH`).

## 1. The host's profile first

In component mode the host may have profiled the tree already. MB does: PRELUDE profiles the root with TraceLens and
gives the result to Arbor as `component.profile`, which the harness reads into your program at every iteration
("The host's profile").

- **What it holds:** `{"unit": "percent", "shares": {<name>: <share>}}`, with its source. The names are ops when
  TraceLens could attribute kernels to ops, and kernel names when it could not (a graph-replayed trace, section 4).
- **Use it:** cite it for where time goes in the root, and rank work by it.
- **Take your own trace** only for what it does not cover: a tree a KEEP has moved, a phase it did not separate
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add amd-agi/hyperloom/profiler@sha256:7317303c6e486449

The line at the top of this page pins the label git:20261105.0d95dc2, 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_qjquyf3ddbwmmrhm.svg)](https://markdownregistry.com/a/art_qjquyf3ddbwmmrhm)

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

Versions

The registry has recorded 1 version of this file, committed on Nov 5, 2026.

versioncommittedcommitsizeaudit
git:20261105.0d95dc2 latest2026-11-05 0d95dc2 5,913 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the 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 (5913 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 · 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_qjquyf3ddbwmmrhm
GET https://markdownregistry.com/api/v1/resolve?ref=amd-agi/hyperloom/profiler
GET https://markdownregistry.com/api/v1/blob/7317303c6e4864497072217478bfbee353c65a37368eb1de3ddd22f08926c1e4

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 A, or by owner.