optimize-gpu-workloads SKILL.md skillA
optimize-gpu-workloads from zystem-io/zymtrace-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add zystem-io/zymtrace-skills/optimize-gpu-workloads@git:20261027.524bf2cPins git:20261027.524bf2c in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- zystem-io/zymtrace-skills
- Path
zymtrace/skills/optimize-gpu-workloads/SKILL.md- Versions recorded
- 2
- Latest version
- git:20261027.524bf2c, committed Oct 27, 2026
- First version recorded
- Jun 8, 2026
- Size
- 13,015 bytes
- Repository stars
- 6
- License
- Apache-2.0
Analyze GPU performance with zymtrace — a GPU workload (NVIDIA CUDA or AMD ROCm), a GPU flamegraph, the hot kernel, why the GPU isn't saturated, or an inference server (vLLM, SGLang, NVIDIA Dynamo-Triton, TensorRT-LLM) or training/fine-tuning job. The zymtrace MCP pulls the data (GPU metrics, flamegraphs); YOU analyze. ALWAYS cross-check the CPU side with the same filter — a GPU workload's bottleneck often hides host-side (tokenizer, DataLoader, Python overhead, sync points) — so pull GPU…
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
# Optimize GPU Workloads > The MCP fetches the data — GPU metrics, flamegraphs; **you** analyze. Load-bearing discipline: **always pull both the GPU and CPU views with the same filter** — half the time a GPU workload's bottleneck is host-side. The common discipline — data-source policy, pre-flight, rank-first vs. drill-down, scope-to-own-code/ROI, the always-recommend-and-apply-the-fix rule, the output-template skeleton, severity sizing, and security — lives in [`shared/analysis-conventions.md`](../../shared/analysis-conventions.md). **Read it.** This skill adds the GPU-specific protocol and call-tree rendering on top. Connection setup lives in [`configure-zymtrace-mcp`](../configure-zymtrace-mcp/SKILL.md); this skill assumes the MCP is connected. **CPU-only workload (no GPUs)?** Use [`optimize-cpu-workloads`](../optimize-cpu-workloads/SKILL.md) — it skips the GPU view, GPU metrics, and inference-server framing entirely. ## Standard starter prompt (for users who don't know what to ask) > **"Analyze the GPU flamegraph over the last 1 hour and suggest solutions."** …
Read the whole file at its exact version.
How to install
mdr add zystem-io/zymtrace-skills/optimize-gpu-workloads@sha256:99898c5e5481c687The line at the top of this page pins the label git:20261027.524bf2c, 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_vmu3urc2udvpixvv)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Jun 8, 2026 and Oct 27, 2026, about one every 142 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261027.524bf2c latest | 2026-10-27 | 524bf2c | 13,015 B | A | view · diff |
| git:20260608.3b7bfd1 | 2026-06-08 | 3b7bfd1 | 10,342 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 (13015 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
zystem-io/zymtrace-skills · 6 stars · license Apache-2.0 · pushed 2026-10-31 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_vmu3urc2udvpixvv GET https://markdownregistry.com/api/v1/resolve?ref=zystem-io/zymtrace-skills/optimize-gpu-workloads GET https://markdownregistry.com/api/v1/blob/99898c5e5481c687a336494333f6f0f41698a8dd2572c9b9fe83cb51afe3f25d
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.