llm-pipeline-analysis
Inspect LLM torch profiler traces at forward-pass, layer, and kernel level. Use when you need layer timings, anchor-kernel…
Return public original model architecture diagrams for user-specified LLM, VLM, MoE, diffusion, OCR, and SGLang/sgl-cookbook model families. Use when the user asks for a model structure chart, architecture diagram, or rendered image link for a specific model such as DeepSeek,
$ npx -y skills add BBuf/AI-Infra-Auto-Driven-SKILLS --skill model-architecture-diagram --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/model-architecture-diagramContext preview
The summary Claude sees to decide when to auto-load this skill.
Return public original model architecture diagrams for user-specified LLM, VLM, MoE, diffusion, OCR, and SGLang/sgl-cookbook model families. Use when the user asks for a model structure chart, architecture diagram, or rendered image link for a specific model such as DeepSeek,
name: model-architecture-diagram description: Return public original model architecture diagrams for user-specified LLM, VLM, MoE, diffusion, OCR, and SGLang/sgl-cookbook model families. Use when the user asks for a model structure chart, architecture diagram, or rendered image link for a specific model such as DeepSeek, GLM, Qwen, Kimi, MiniMax, Step, Hunyuan, or Qwen3-VL.
Return only public original diagrams indexed by this skill.
1. Run the bundled resolver:
python3 skills/model-architecture-diagram/scripts/model_architecture_diagram.py "<model name>"
2. If the resolver returns `kind: existing`, return the raw image Markdown it prints and preserve the source attribution line. 3. If the resolver returns `kind: no_match`, tell the user that no public original architecture diagram is indexed for that model.
Use `references/diagram-index.json` as the source of truth. It stores raw GitHub image URLs and official vendor/CDN or pinned Hugging Face `resolve/<sha>` URLs. Official sources include Qwen and XiaomiMiMo; GitHub sources:
Prefer detailed implementation, cookbook, or architecture-card diagrams over paper figures. Good sources show module boundaries, dataflow, MoE / attention / cache paths, or model-specific runtime structure rather than only a high-level paper overview. Official repository diagrams and curated implementation diagrams are first choice; paper figures are fallback only when no more detailed public original diagram is indexed.
Do not copy remote image binaries into the skill. Return the indexed original URLs so the chat renderer can display the original image.
For a direct match, show the original image. Good direct matches include:
If multiple diagrams match, show all high-confidence matches up to the resolver's default limit. For example, DeepSeek V3 may return the full architecture plus MLA MHA/MQA diagrams.
Do not commit the `sgl-cookbook-model-architecture-images/` gallery into the repository. The public-original image set is hosted as a GitHub Release asset and indexed by a GitHub issue.
Current hosted artifact:
The gallery is a 2026-05-02 snapshot containing 44 public original diagram image files; it does not mirror the current index, plus a lightweight `index.html`, `index.md`, `manifest.json`, HTML contact sheet, and `architecture-audit.md`.
To inspect the gallery locally:
curl -L -o /tmp/sgl-cookbook-model-architecture-images-2026-05-02.zip \ https://github.com/BBuf/AI-Infra-Auto-Driven-SKILLS/releases/download/sgl-cookbook-architecture-images-2026-05-02/sgl-cookbook-model-architecture-images-2026-05-02.zip unzip -q /tmp/sgl-cookbook-model-architecture-images-2026-05-02.zip -d /tmp open /tmp/sgl-cookbook-model-architecture-images/index.html
List known original diagram aliases:
python3 skills/model-architecture-diagram/scripts/model_architecture_diagram.py --list-known
Emit JSON for automation:
python3 skills/model-architecture-diagram/scripts/model_architecture_diagram.py "GLM-5" --format json
**Agent-ready skills for LLM serving benchmarks, profiler triage, capacity planning, model Day-0 support, code review, incident triage, and model PR history across SGLang, vLLM, TensorRT-LLM, and TokenSpeed — plus SGLang PR and article explainer videos.**
Inspect LLM torch profiler traces at forward-pass, layer, and kernel level. Use when you need layer timings, anchor-kernel…
Framework-independent LLM serving benchmark skill for comparing SGLang, vLLM, TensorRT-LLM, TokenSpeed, or another serving…
Parse SGLang/vLLM startup logs to explain GPU memory use and request capacity. Use for KV cache budget, mem-fraction-static…
Analyze existing Torch Profiler Chrome traces or capture from SGLang, vLLM, TensorRT-LLM and TokenSpeed servers. Return kernel…
Build an operator-level compute template for an LLM and estimate FLOPs/MFU for a serving shape. Use when you need tensor shapes,…
Build or audit an evidence-driven SGLang Day-0 support program for a new LLM, VLM, MoE, hybrid-attention, or speculative-decoding…