AI-Infra-Auto-Driven-SKILLS for Codex

Skills (12)

• model-pr-optimization-history — Use when an SGLang, vLLM, TensorRT-LLM, or TokenSpeed serving/model optimization task needs prior model-family PR evidence. Query and read the PR-driven history docs under model-pr-optimization-history before choosing source paths, fast paths, kernel/fusion…
• llm-pipeline-analysis — Inspect LLM torch profiler traces at forward-pass, layer, and kernel level. Use when you need layer timings, anchor-kernel boundaries, representative kernel flows, or Perfetto time ranges.
• llm-serving-auto-benchmark — Framework-independent LLM serving benchmark skill for comparing SGLang, vLLM, TensorRT-LLM, TokenSpeed, or another serving framework. Use when a user wants to find the best deployment command for one model across multiple serving frameworks under the same…
• llm-serving-capacity-planner — 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.
• llm-torch-profiler-analysis — Analyze existing Torch Profiler Chrome traces or capture from SGLang, vLLM, TensorRT-LLM and TokenSpeed servers. Return kernel attribution, overlap opportunities and fusion patterns; use for model dispatch, CUDA Graph gaps, stream contention or exposed…
• model-architecture-diagram — 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…
• model-compute-simulation — 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.
• sglang-explainer-video — Turn an SGLang PR (number or URL) or a technical article (Markdown path) into a Chinese explainer video that fully explains every algorithm and code change (length follows the material, no time cap) — natural edge-tts narration, word-synced bilingual…
• sglang-humanize-review — Perform SGLang code review in the style of human maintainers by consulting the public PR review episode corpus from project start through 2026-07-27, including inline review threads, top-level PR comments, review submissions, original multilingual text, and…
• sglang-prod-incident-triage — Replay-first debug flow for SGLang serving problems. Use when a live or recent server shows health-check failures, latency or throughput regressions, queue growth, timeouts, distributed stalls, crash dumps, wrong outputs after deploys, or PD/EP/HiCache…
• torch-profiler-layer-track — Add verified layer-number guides and compact GPU display lanes to an existing Torch Profiler Chrome JSON trace. Use for L0/L1/... navigation or traces with hundreds of CUDA Graph stream rows. Changes visualization, not runtime streams.
• sglang-model-day0-support — Build or audit an evidence-driven SGLang Day-0 support program for a new LLM, VLM, MoE, hybrid-attention, or speculative-decoding model. Use when Codex needs to map a model architecture into SGLang runtime work, design a public support PR DAG, create…