llm-serving-capacity-planner SKILL.md skillA
llm-serving-capacity-planner 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.
mdr add bbuf/ai-infra-auto-driven-skills/llm-serving-capacity-planner@git:20261005.aa3fee7Pins 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/llm-serving-capacity-planner/SKILL.md- Versions recorded
- 5
- Latest version
- git:20261005.aa3fee7, committed Oct 5, 2026
- First version recorded
- Jul 28, 2026
- Size
- 10,079 bytes
- Repository stars
- 1,120
- License
- none declared
Parse SGLang/vLLM startup logs to explain GPU memory use and request capacity. Use for KV cache budget, mem-fraction-static comparisons, OOM triage, and max-concurrency estimates.
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
# LLM Serving Capacity Planner ## Overview Use this when a serving log has enough memory lines to explain where GPU HBM went. The analyzer reads SGLang/vLLM startup logs, extracts weight load, KV pool, CUDA graph, framework overhead, and token-capacity lines, then estimates concurrent requests for common token lengths. For DeepSeek-V4.1, read the [KV layout and page-allocation contract](../llm-torch-profiler-analysis/references/fuse-overlap-catalog.md#paged-kv-storage-contract) before using 528 B/288 B in an estimate. These are per-stored-token payload and scale sizes, not allocation after page padding or total model KV bytes. Verify actual pool layout, compression ratios and sharing from the pinned source and logs. ## Inputs Before running analysis, collect or verify these inputs: | Item | Why it matters | How to obtain | Default if user skips | |---|---|---|---| | Log file path | Primary input; all memory data comes from here | Ask user for the serving startup log | — (required) | | GPU type | Determines total HBM for decomposition validation | Ask user or infer from log | Auto-detected from log if possible | …
Read the whole file at its exact version.
How to install
mdr add bbuf/ai-infra-auto-driven-skills/llm-serving-capacity-planner@sha256:a18feefc65aed9cdThe 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.
[](https://markdownregistry.com/a/art_f46yhzzgpgqg6kmi)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Jul 28, 2026 and Oct 5, 2026, about one every 17 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261005.aa3fee7 latest | 2026-10-05 | aa3fee7 | 10,079 B | A | view · diff |
| git:20260922.475af5a | 2026-09-22 | 475af5a | 8,473 B | A | view · diff |
| git:20260918.b4657a2 | 2026-09-18 | b4657a2 | 8,050 B | A | view · diff |
| git:20260823.c7b7857 | 2026-08-23 | c7b7857 | 7,802 B | A | view · diff |
| git:20260728.98fd73c | 2026-07-28 | 98fd73c | 7,302 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (10079 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
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_f46yhzzgpgqg6kmi GET https://markdownregistry.com/api/v1/resolve?ref=bbuf/ai-infra-auto-driven-skills/llm-serving-capacity-planner GET https://markdownregistry.com/api/v1/blob/a18feefc65aed9cd1f43469d56a4ed2a5b3e86a3da34c4de61d3d635124a9bd4
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.