model-compute-simulation SKILL.md skillA

model-compute-simulation from bbuf/ai-infra-auto-driven-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add bbuf/ai-infra-auto-driven-skills/model-compute-simulation@git:20261005.aa3fee7

Pins git:20261005.aa3fee7 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
bbuf/ai-infra-auto-driven-skills
Path
skills/model-compute-simulation/SKILL.md
Versions recorded
5
Latest version
git:20261005.aa3fee7, committed Oct 5, 2026
First version recorded
May 20, 2026
Size
18,121 bytes
Repository stars
1,120
License
none declared

Build an operator-level compute template for an LLM and estimate FLOPs/MFU for a serving shape. Use when you need tensor shapes, per-op FLOPs, kernel-to-op MFU mapping, or parallelism what-if analysis.

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

# Model Compute Simulation

## Overview

Use this when the question is about operator order, tensor dimensions, FLOPs,
MFU, or parallelism checks. The simulator loads a model config, builds the
representative operator sequence, prints tensor shapes and FLOPs, and can
estimate MFU from measured latency.

## Inputs

Before running a simulation, collect or verify these inputs:

| Item | Why it matters | How to obtain | Default if user skips |
|---|---|---|---|
| Model name | Resolves to config in `model-config-index.json`; determines entire architecture | Ask user or infer from trace context | — (required) |
| Config accuracy | Indexed values may differ from actual serving config (e.g. `routed_expert_intermediate_size`, `compress_ratios`) | Ask user to provide `config.json` or verify key params against HuggingFace | Use indexed values with a caveat |
| GPU type | Determines peak FLOPS for MFU denominator | Ask user | — (required for MFU) |
| dtype (bf16 / fp8) | Affects peak FLOPS selection; fp8 doubles peak | Ask user | bf16 |
| Batch size & seq len | Directly affects FLOPs and tensor shapes | Ask user | B=1, S=1 (decode) |
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add bbuf/ai-infra-auto-driven-skills/model-compute-simulation@sha256:669641369a41dbed

The line at the top of this page pins the label git:20261005.aa3fee7, 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_5owrcejbvvbepr6s.svg)](https://markdownregistry.com/a/art_5owrcejbvvbepr6s)

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

Versions

The registry has recorded 5 versions of this file, between May 20, 2026 and Oct 5, 2026, about one every 34 days.

versioncommittedcommitsizeaudit
git:20261005.aa3fee7 latest2026-10-05 aa3fee7 18,121 BA view · diff
git:20260918.b4657a22026-09-18 b4657a2 15,486 BA view · diff
git:20260823.c7b78572026-08-23 c7b7857 14,526 BA view · diff
git:20260728.98fd73c2026-07-28 98fd73c 14,314 BA view · diff
git:20260520.ab324552026-05-20 ab32455 13,351 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 (18121 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

bbuf/ai-infra-auto-driven-skills · 1,120 stars · license none declared · pushed 2026-11-08 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_5owrcejbvvbepr6s
GET https://markdownregistry.com/api/v1/resolve?ref=bbuf/ai-infra-auto-driven-skills/model-compute-simulation
GET https://markdownregistry.com/api/v1/blob/669641369a41dbeddf628e35f5038b345e07c133d581c637b63b910bec81a2e3

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 bbuf/ai-infra-auto-driven-skills

model-pr-history-knowledge SKILL.md skill
bbuf/ai-infra-auto-driven-skills · model-pr-optimization-history/SKILL.md · Use when an SGLang, vLLM, TensorRT-LLM, or TokenSpeed serving/model optimization task needs prior model-family PR…
git:20261005.aa3fee7 · audit A · 1,120 stars
llm-pipeline-analysis SKILL.md skill
bbuf/ai-infra-auto-driven-skills · skills/llm-pipeline-analysis/SKILL.md · Inspect LLM torch profiler traces at forward-pass, layer, and kernel level. Use when you need layer timings…
git:20261005.aa3fee7 · audit A · 1,120 stars
llm-serving-auto-benchmark SKILL.md skill
bbuf/ai-infra-auto-driven-skills · skills/llm-serving-auto-benchmark/SKILL.md · Framework-independent LLM serving benchmark skill for comparing SGLang, vLLM, TensorRT-LLM, TokenSpeed, or another…
git:20261005.aa3fee7 · audit B · 1,120 stars
llm-serving-capacity-planner SKILL.md skill
bbuf/ai-infra-auto-driven-skills · skills/llm-serving-capacity-planner/SKILL.md · Parse SGLang/vLLM startup logs to explain GPU memory use and request capacity. Use for KV cache budget…
git:20261005.aa3fee7 · audit A · 1,120 stars
llm-torch-profiler-analysis SKILL.md skill
bbuf/ai-infra-auto-driven-skills · skills/llm-torch-profiler-analysis/SKILL.md · Analyze existing Torch Profiler Chrome traces or capture from SGLang, vLLM, TensorRT-LLM and TokenSpeed servers. Return…
git:20261005.aa3fee7 · audit B · 1,120 stars
model-architecture-diagram SKILL.md skill
bbuf/ai-infra-auto-driven-skills · skills/model-architecture-diagram/SKILL.md · Return public original model architecture diagrams for user-specified LLM, VLM, MoE, diffusion, OCR, and…
git:20261005.aa3fee7 · audit A · 1,120 stars
sglang-model-day0-support SKILL.md skill
bbuf/ai-infra-auto-driven-skills · skills/model-optimization/sglang-model-day0-support/SKILL.md · Build or audit an evidence-driven SGLang Day-0 support program for a new LLM, VLM, MoE, hybrid-attention, or…
git:20261005.aa3fee7 · audit A · 1,120 stars
sglang-explainer-video SKILL.md skill
bbuf/ai-infra-auto-driven-skills · skills/sglang-explainer-video/SKILL.md · Turn an SGLang PR (number or URL) or a technical article (Markdown path) into a Chinese explainer video that fully…
git:20261107.b47f67f · audit A · 1,120 stars
sglang-prod-incident-triage SKILL.md skill
bbuf/ai-infra-auto-driven-skills · skills/sglang-prod-incident-triage/SKILL.md · Replay-first debug flow for SGLang serving problems. Use when a live or recent server shows health-check failures…
git:20261005.aa3fee7 · audit B · 1,120 stars
torch-profiler-layer-track SKILL.md skill
bbuf/ai-infra-auto-driven-skills · skills/torch-profiler-layer-track/SKILL.md · Add verified layer-number guides and compact GPU display lanes to an existing Torch Profiler Chrome JSON trace. Use for…
git:20261005.aa3fee7 · audit B · 1,120 stars

Every file in bbuf/ai-infra-auto-driven-skills

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