LLM serving benchmarks, SGLang model Day-0 support, profiling, code review, prod incident triage, PR-history dossiers, and SGLang explainer videos.
Plugin ai-infra-auto-driven-skills from marketplace ai-infra-auto-driven-skills in BBuf/AI-Infra-Auto-Driven-SKILLS. Commands read from the repo's manifest — 3 days ago.
model-pr-history-knowledgeUse 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 ideas, regression risks, or validation lan
llm-pipeline-analysisInspect 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-benchmarkFramework-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 workload, GPU budget, and latency SLA.
llm-serving-capacity-plannerParse 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-analysisAnalyze 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 kernel tails. Includes existing SGLang Omni tra
model-architecture-diagramReturn 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, MiniMa
model-compute-simulationBuild 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-model-day0-supportBuild 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 validation and release gates, sanitize private de
sglang-explainer-videoTurn 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 中文/English captions, the orange "SGLang PR 讲解 / S
sglang-prod-incident-triageReplay-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 issues, and the job is to turn the problem into
torch-profiler-layer-trackAdd 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.
AMD's verified Agent Skills in one plugin: route image/audio through local AI on Ryzen AI, serve LLMs on AMD Instinct GPUs with vLLM, optimize inference throughput with Hyperloom, and analyze GPU kernel and PyTorch trace performance.
21 skills
Production LLM inference including vLLM, TensorRT-LLM, llama.cpp, and SGLang. Use when deploying models for production inference.
98 skills
Claude Code plugin for sparkrun - launch, manage, and stop LLM inference workloads on NVIDIA DGX Spark systems. Provides slash commands and skills for recipe browsing, cluster management, and multi-node orchestration.
3 skills · 8 commands
AMD's verified Agent Skills in one plugin: route image/audio through local AI on Ryzen AI, serve LLMs on AMD Instinct GPUs with vLLM, optimize inference throughput with Hyperloom, and analyze GPU kernel and PyTorch trace performance.
1 skill
从 gitcode-ascend 同步的 Ascend 技能集，包含 91 个技能： - analyse-coverage: 分析测试覆盖率盲区，生成覆盖率分析报告 - arxiv-recommendation-npu: 自动化推荐系统论文发现流水线。抓取 arxiv 推荐论文，检测源码，生成待迁移任务清单，由 npu-model-migration skill 完成 NPU 适配。 - ascend-inference-repos-copilot: 昇腾（Ascend）推理生态开源代码仓库智能问答专家旨在为 vLLM、vLLM-Ascend、MindIE-LLM、MindIE-SD、MindIE-Motor、MindIE-Turbo 以及 msM - ... 等 88 个技能
191 skills
Operate, configure, benchmark, and troubleshoot vLLM inference servers: Docker and Kubernetes deployment, quantization-aware model configuration (tensor parallelism, KV cache), OpenAI-compatible API serving, throughput and latency benchmarking, continuous batching tuning, GPU operation, and upgrade/rollback. Use when deploying or running a vLLM server (vllm serve, vllm/vllm-openai), sizing a model and its KV cache for GPUs, selecting quantization and parallelism, serving via /v1 endpoints, measuring serving throughput or latency, tuning batching, or diagnosing GPU, OOM, or startup failures in a vLLM deployment. Do not use for model training, fine-tuning, evaluation-set design, or engine-selection methodology (that is ml-engineering), or for operating the llama.cpp stack with GGUF models (that is llama-cpp); other inference engines (TGI, Ollama, Triton) are out of scope.
194 skills
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.