[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M73GF47RMBVRX32P04T26Z8V":3,"skill-same:01M73GF47RMBVRX32P04T26Z8V":47},{"skillNo":4,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":28,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M73GF47RMBVRX32P04T26Z8V","triton-inference-server",null,"Horonomos-laps\u002FYana-AI","Horonomos-laps","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F355299122?v=4","01M76B3QPXE88ET2SQPDPVATZT"," Horonomos-laps","01M72ZQRJPCYPSSWT4D00VJR2A",13,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Ftriton-inference-server\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: triton-inference-server\ndescription: NVIDIA Triton Inference Server for production GPU model serving. Model repository layout, dynamic batching, concurrent model execution, gRPC\u002FHTTP clients, and ensemble pipelines. Sources: triton-inference-server\u002Fserver (BSD-3-Clause).\norigin: yana-ai — synthesized from triton-inference-server\u002Fserver (BSD-3-Clause)\nlicense: Apache-2.0\nversion: 1.0.0\ncompatibility: yana-ai >= 1.3.51\n---\n\n# \u002Ftriton-inference-server\n\n## When to Use\n\n- Multi-model GPU serving: run 10+ models on one server with resource isolation\n- Dynamic batching: automatically group concurrent requests to maximize GPU utilization\n- Ensemble pipelines: chain preprocessing → inference → postprocessing as a single request\n- Production SLA: per-model instance groups with priority scheduling\n\n## Do NOT use for\n\n- Development\u002Flocal inference (use [[llama-cpp-quantization]] or [[vllm-paged-attention]])\n- Models not in TensorRT\u002FONNX\u002FTensorFlow\u002FPyTorch\u002FPython backend format\n\n---\n\n## Model repository layout\n\n```\nmodel_repository\u002F\n├── sentiment\u002F\n│   ├── config.pbtxt\n│   └── 1\u002F\n│       └── model.onnx           ← versioned model artifact\n├── embedding\u002F\n│   ├── config.pbtxt\n│   └── 1\u002F\n│       └── model.plan           ← TensorRT engine\n└── text_pipeline\u002F\n    ├── config.pbtxt             ← ensemble config\n    └── 1\u002F\n        └── (no artifact for ensemble)\n```\n\n---\n\n## config.pbtxt (ONNX model)\n\n```protobuf\nname:     \"sentiment\"\nbackend:  \"onnxruntime\"\nmax_batch_size: 32\n\ninput [{\n  name:     \"input_ids\"\n  data_type: TYPE_INT64\n  dims:     [-1]    # dynamic sequence length\n}]\noutput [{\n  name:     \"logits\"\n  data_type: TYPE_FP32\n  dims:     [2]\n}]\n\ndynamic_batching {\n  preferred_batch_size: [8, 16, 32]\n  max_queue_delay_microseconds: 5000   # wait up to 5ms to fill a batch\n}\n\ninstance_group [{\n  count: 2       # 2 concurrent GPU instances\n  kind:  KIND_GPU\n  gpus:  [0]\n}]\n```\n\n---\n\n## HTTP client (Node.js)\n\n```javascript\nasync function tritonInfer(modelName: string, inputData: Float32Array): Promise\u003CFloat32Array> {\n  const res = await fetch(`http:\u002F\u002Ftriton:8000\u002Fv2\u002Fmodels\u002F${modelName}\u002Finfer`, {\n    method:  'POST',\n    headers: { 'Content-Type': 'application\u002Fjson' },\n    body: JSON.stringify({\n      inputs: [{\n        name:     'input_ids',\n        shape:    [1, inputData.length],\n        datatype: 'INT64',\n        data:     Array.from(inputData),\n      }],\n      outputs: [{ name: 'logits' }],\n    }),\n  })\n\n  if (!res.ok) throw new Error(`[triton] ${res.status}: ${await res.text()}`)\n  const result = await res.json()\n  return new Float32Array(result.outputs[0].data)\n}\n```\n\n---\n\n## Ensemble pipeline config\n\n```protobuf\n# text_pipeline\u002Fconfig.pbtxt — tokenize → infer → decode\nname:     \"text_pipeline\"\nplatform: \"ensemble\"\nmax_batch_size: 32\n\ninput  [{ name: \"raw_text\",  data_type: TYPE_STRING, dims: [1] }]\noutput [{ name: \"label\",     data_type: TYPE_STRING, dims: [1] }]\n\nensemble_scheduling {\n  step [\n    { model_name: \"tokenizer\",  model_version: -1,\n      input_map  { key: \"raw_text\" value: \"raw_text\" }\n      output_map { key: \"input_ids\" value: \"input_ids\" } },\n    { model_name: \"sentiment\",  model_version: -1,\n      input_map  { key: \"input_ids\" value: \"input_ids\" }\n      output_map { key: \"logits\" value: \"logits\" } },\n    { model_name: \"postprocess\", model_version: -1,\n      input_map  { key: \"logits\" value: \"logits\" }\n      output_map { key: \"label\" value: \"label\" } },\n  ]\n}\n```\n\n---\n\n## Anti-Fake-Pass Checklist\n\n```\n❌ max_batch_size: 0 → batching disabled; dynamic batching has no effect\n❌ dims: [128] (static) → rejects variable-length inputs; use [-1] for dynamic\n❌ instance_group KIND_GPU without CUDA → Triton falls back to CPU silently\n❌ Ensemble step output_map key mismatch → pipeline fails with cryptic shape error\n❌ No max_queue_delay_microseconds → batches wait forever for preferred_batch_size\n❌ Triton HTTP (not gRPC) for large tensors → JSON encoding overhead; use gRPC for FP32 arrays\n```\n","# \u002Ftriton-inference-server\n\n## When to Use\n\n- Multi-model GPU serving: run 10+ models on one server with resource isolation\n- Dynamic batching: automatically group concurrent requests to maximize GPU utilization\n- Ensemble pipelines: chain preprocessing → inference → postprocessing as a single request\n- Production SLA: per-model instance groups with priority scheduling\n\n## Do NOT use for\n\n- Development\u002Flocal inference (use [[llama-cpp-quantization]] or [[vllm-paged-attention]])\n- Models not in TensorRT\u002FONNX\u002FTensorFlow\u002FPyTorch\u002FPython backend format\n\n---\n\n## Model repository layout\n\n```\nmodel_repository\u002F\n├── sentiment\u002F\n│   ├── config.pbtxt\n│   └── 1\u002F\n│       └── model.onnx           ← versioned model artifact\n├── embedding\u002F\n│   ├── config.pbtxt\n│   └── 1\u002F\n│       └── model.plan           ← TensorRT engine\n└── text_pipeline\u002F\n    ├── config.pbtxt             ← ensemble config\n    └── 1\u002F\n        └── (no artifact for ensemble)\n```\n\n---\n\n## config.pbtxt (ONNX model)\n\n```protobuf\nname:     \"sentiment\"\nbackend:  \"onnxruntime\"\nmax_batch_size: 32\n\ninput [{\n  name:     \"input_ids\"\n  data_type: TYPE_INT64\n  dims:     [-1]    # dynamic sequence length\n}]\noutput [{\n  name:     \"logits\"\n  data_type: TYPE_FP32\n  dims:     [2]\n}]\n\ndynamic_batching {\n  preferred_batch_size: [8, 16, 32]\n  max_queue_delay_microseconds: 5000   # wait up to 5ms to fill a batch\n}\n\ninstance_group [{\n  count: 2       # 2 concurrent GPU instances\n  kind:  KIND_GPU\n  gpus:  [0]\n}]\n```\n\n---\n\n## HTTP client (Node.js)\n\n```javascript\nasync function tritonInfer(modelName: string, inputData: Float32Array): Promise\u003CFloat32Array> {\n  const res = await fetch(`http:\u002F\u002Ftriton:8000\u002Fv2\u002Fmodels\u002F${modelName}\u002Finfer`, {\n    method:  'POST',\n    headers: { 'Content-Type': 'application\u002Fjson' },\n    body: JSON.stringify({\n      inputs: [{\n        name:     'input_ids',\n        shape:    [1, inputData.length],\n        datatype: 'INT64',\n        data:     Array.from(inputData),\n      }],\n      outputs: [{ name: 'logits' }],\n    }),\n  })\n\n  if (!res.ok) throw new Error(`[triton] ${res.status}: ${await res.text()}`)\n  const result = await res.json()\n  return new Float32Array(result.outputs[0].data)\n}\n```\n\n---\n\n## Ensemble pipeline config\n\n```protobuf\n# text_pipeline\u002Fconfig.pbtxt — tokenize → infer → decode\nname:     \"text_pipeline\"\nplatform: \"ensemble\"\nmax_batch_size: 32\n\ninput  [{ name: \"raw_text\",  data_type: TYPE_STRING, dims: [1] }]\noutput [{ name: \"label\",     data_type: TYPE_STRING, dims: [1] }]\n\nensemble_scheduling {\n  step [\n    { model_name: \"tokenizer\",  model_version: -1,\n      input_map  { key: \"raw_text\" value: \"raw_text\" }\n      output_map { key: \"input_ids\" value: \"input_ids\" } },\n    { model_name: \"sentiment\",  model_version: -1,\n      input_map  { key: \"input_ids\" value: \"input_ids\" }\n      output_map { key: \"logits\" value: \"logits\" } },\n    { model_name: \"postprocess\", model_version: -1,\n      input_map  { key: \"logits\" value: \"logits\" }\n      output_map { key: \"label\" value: \"label\" } },\n  ]\n}\n```\n\n---\n\n## Anti-Fake-Pass Checklist\n\n```\n❌ max_batch_size: 0 → batching disabled; dynamic batching has no effect\n❌ dims: [128] (static) → rejects variable-length inputs; use [-1] for dynamic\n❌ instance_group KIND_GPU without CUDA → Triton falls back to CPU silently\n❌ Ensemble step output_map key mismatch → pipeline fails with cryptic shape error\n❌ No max_queue_delay_microseconds → batches wait forever for preferred_batch_size\n❌ Triton HTTP (not gRPC) for large tensors → JSON encoding overhead; use gRPC for FP32 arrays\n```\n",{},"main","481dcd7dd2e288b9d627a2bd017db70e64e6c6fa","core\u002Fskills\u002Ftriton-inference-server",1,"https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI","https:\u002F\u002Fyana.vutam.link\u002F","https:\u002F\u002Fgithub.com\u002FHoronomos-laps","https:\u002F\u002Fyana.vutam.link","An open-source governed runtime & execution environment for multi-agent AI systems.","2026-11-11 23:56:26",{"source":7,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add Horonomos-laps\u002FYana-AI --skill triton-inference-server",{"tool":39,"command":40},"bunx","bunx skills add Horonomos-laps\u002FYana-AI --skill triton-inference-server",{"tool":42,"command":43},"pnpm","pnpm dlx skills add Horonomos-laps\u002FYana-AI --skill triton-inference-server","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Ftriton-inference-server\u002FSKILL.md",true,[],[48,56,63,71,79,87],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":52,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":18},"01M735GKET5YVYKAY62W2P5YXB","openai--sentry--sentry","Use when the user asks to inspect Sentry issues or events, summarize recent production errors, or pull basic Sentry health data via the Sentry API; perform read-only queries with the bundled script and require `SENTRY_AUTH_TOKEN`.","MIT","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fopenai--sentry--sentry\u002FSKILL.md",[],[],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":18},"01M73DCAP83T17HY7SMGK7MGFE","ito-basket-compare","Compare Itô prediction-market baskets against a user's knowledge base, portfolio notes, financial context, watchlist, or research thesis. Use for read-only basket comparison and gap analysis without investment advice or live trading.","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fito-basket-compare\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":67,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":18},"01M734CYEMZFDR3KH6SW0JP8TD","implementing-network-traffic-baselining","Build network traffic baselines from NetFlow\u002FIPFIX data using Python pandas for statistical analysis, z-score anomaly detection, and hourly\u002Fdaily traffic pattern profiling","https:\u002F\u002Fgithub.com\u002Fyanacuti1121\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-network-traffic-baselining\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-network-traffic-baselining\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":75,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":18},"01M73ASZ6NJRJM44Z2P84NGQ3Q","detecting-evasion-techniques-in-endpoint-logs","Detects defense evasion techniques used by adversaries in endpoint logs including log tampering, timestomping, process injection, and security tool disabling. Use when investigating suspicious endpoint behavior, building detection rules for evasion tactics, or conducting threat hunting for stealthy adversary activity. Activates for requests involving evasion detection, defense evasion analysis, log tampering detection, or MITRE ATT&CK TA0005.","https:\u002F\u002Fgithub.com\u002Fyanacuti1121\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fdetecting-evasion-techniques-in-endpoint-logs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fdetecting-evasion-techniques-in-endpoint-logs\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":83,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":18},"01M734AFNXD06Z78QRK0VKGT7Q","implementing-microsegmentation-with-guardicore","Implementing microsegmentation using Akamai Guardicore Segmentation to map application dependencies, create granular network policies, visualize east-west traffic flows, and enforce least-privilege communication between workloads across data centers and cloud.","https:\u002F\u002Fgithub.com\u002Fyanacuti1121\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-microsegmentation-with-guardicore\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-microsegmentation-with-guardicore\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":18},"01M736TK27QMCXK0DVCH25SJN5","ramdisk-tmpfs-patterns","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Framdisk-tmpfs-patterns\u002FSKILL.md",[],[]]