[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7928RBP83V9B13WWA5C7F22":3,"skill-same:01M7928RBP83V9B13WWA5C7F22":70},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"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":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":32,"install":33,"resources":45},"01M7928RBP83V9B13WWA5C7F22","serving",null,"Guide Otter controller, worker, Gradio, local CLI, endpoint, import, port, and load-bit serving workflows.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"MIT","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fotter\u002Fsub-skills\u002Fserving\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: serving\ndescription: \"Guide Otter controller, worker, Gradio, local CLI, endpoint,\n  import, port, and load-bit serving workflows.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Otter serving sub-skill\n\nUse this sub-skill when the task is to expose Otter or Flamingo generation through a local controller\u002Fworker service, Gradio image\u002Fvideo UI, direct text-generation CLI, or HTTP streaming endpoint.\n\n## Route here for\n\n- Controller, model-worker, Gradio image UI, Gradio video UI, worker registration, heartbeats, and queue dispatch.\n- Model-worker options such as `--checkpoint_path`, `--model_name`, `--num_gpus`, `--load_bit`, controller\u002Fworker URLs, and concurrency.\n- Streaming request payloads containing `prompt`, optional base64 image\u002Fvideo frames, and `generation_kwargs`.\n- Debugging known serving import problems, dependency\u002Fversion issues, missing constants, bad ports, registration failures, and GPU\u002Fload-bit problems.\n- Local text-only CLI generation with `--model-name`, `--device`, `--num-gpus`, and conversation templates.\n\n## Route away\n\n- Ad hoc package\u002FAPI inference or YAML batch prompt files: [model-inference](..\u002Fmodel-inference\u002FSKILL.md).\n- Training, finetuning, Accelerate\u002FDeepSpeed, and checkpoint save cadence: [training](..\u002Ftraining\u002FSKILL.md).\n- Benchmark configs and evaluator registries: [benchmark-evaluation](..\u002Fbenchmark-evaluation\u002FSKILL.md).\n- MIMIC-IT data conversion, Syphus, and schema validation: [data-preparation](..\u002Fdata-preparation\u002FSKILL.md).\n\n## Operating workflow\n\n1. Decide whether the user needs a three-process web demo, a direct local CLI, or endpoint\u002FAPI debugging.\n2. Read [serving topology](references\u002Fserving-topology.md) for controller, worker, Gradio, and local CLI roles.\n3. Generate safe command templates with [build_serving_commands.py](scripts\u002Fbuild_serving_commands.py). The helper prints commands only; it never starts servers or loads models.\n4. Before launching anything, run [check_serving_imports.py](scripts\u002Fcheck_serving_imports.py) in the target environment. Use `--repo-root` only when the user is working in an Otter checkout and wants checkout-specific diagnostics.\n5. For endpoint shapes and worker payloads, read [API reference](references\u002Fapi-reference.md).\n6. For failures involving `pipeline.constants`, Gradio versions, worker registration, GPU memory, image payloads, or stalled streaming, use [troubleshooting](references\u002Ftroubleshooting.md).\n\n## Quick reference map\n\n| Need | Start with |\n|---|---|\n| Three-process controller + worker + Gradio plan | [serving topology](references\u002Fserving-topology.md#three-process-demo-topology) |\n| Generate commands with custom ports\u002Fmodel path | [build_serving_commands.py](scripts\u002Fbuild_serving_commands.py) |\n| Check imports without starting services | [check_serving_imports.py](scripts\u002Fcheck_serving_imports.py) |\n| Understand controller\u002Fworker endpoints | [API reference](references\u002Fapi-reference.md) |\n| Diagnose missing `pipeline.constants` or `flamingo` import | [troubleshooting](references\u002Ftroubleshooting.md#known-checkout-import-defects) |\n| Choose `fp16`, `bf16`, `int8`, `int4`, or `fp32` | [serving topology](references\u002Fserving-topology.md#worker-model-loading-choices) |\n\n## Safety boundary\n\nServing launches long-running processes, opens network ports, can download or load large checkpoints, and may allocate multiple GPUs. Do not start controller, worker, Gradio, or Flask services unless the user supplies the model\u002Fcheckpoint, host\u002Fport policy, GPU budget, and explicit permission to launch them.\n","# Otter serving sub-skill\n\nUse this sub-skill when the task is to expose Otter or Flamingo generation through a local controller\u002Fworker service, Gradio image\u002Fvideo UI, direct text-generation CLI, or HTTP streaming endpoint.\n\n## Route here for\n\n- Controller, model-worker, Gradio image UI, Gradio video UI, worker registration, heartbeats, and queue dispatch.\n- Model-worker options such as `--checkpoint_path`, `--model_name`, `--num_gpus`, `--load_bit`, controller\u002Fworker URLs, and concurrency.\n- Streaming request payloads containing `prompt`, optional base64 image\u002Fvideo frames, and `generation_kwargs`.\n- Debugging known serving import problems, dependency\u002Fversion issues, missing constants, bad ports, registration failures, and GPU\u002Fload-bit problems.\n- Local text-only CLI generation with `--model-name`, `--device`, `--num-gpus`, and conversation templates.\n\n## Route away\n\n- Ad hoc package\u002FAPI inference or YAML batch prompt files: [model-inference](..\u002Fmodel-inference\u002FSKILL.md).\n- Training, finetuning, Accelerate\u002FDeepSpeed, and checkpoint save cadence: [training](..\u002Ftraining\u002FSKILL.md).\n- Benchmark configs and evaluator registries: [benchmark-evaluation](..\u002Fbenchmark-evaluation\u002FSKILL.md).\n- MIMIC-IT data conversion, Syphus, and schema validation: [data-preparation](..\u002Fdata-preparation\u002FSKILL.md).\n\n## Operating workflow\n\n1. Decide whether the user needs a three-process web demo, a direct local CLI, or endpoint\u002FAPI debugging.\n2. Read [serving topology](references\u002Fserving-topology.md) for controller, worker, Gradio, and local CLI roles.\n3. Generate safe command templates with [build_serving_commands.py](scripts\u002Fbuild_serving_commands.py). The helper prints commands only; it never starts servers or loads models.\n4. Before launching anything, run [check_serving_imports.py](scripts\u002Fcheck_serving_imports.py) in the target environment. Use `--repo-root` only when the user is working in an Otter checkout and wants checkout-specific diagnostics.\n5. For endpoint shapes and worker payloads, read [API reference](references\u002Fapi-reference.md).\n6. For failures involving `pipeline.constants`, Gradio versions, worker registration, GPU memory, image payloads, or stalled streaming, use [troubleshooting](references\u002Ftroubleshooting.md).\n\n## Quick reference map\n\n| Need | Start with |\n|---|---|\n| Three-process controller + worker + Gradio plan | [serving topology](references\u002Fserving-topology.md#three-process-demo-topology) |\n| Generate commands with custom ports\u002Fmodel path | [build_serving_commands.py](scripts\u002Fbuild_serving_commands.py) |\n| Check imports without starting services | [check_serving_imports.py](scripts\u002Fcheck_serving_imports.py) |\n| Understand controller\u002Fworker endpoints | [API reference](references\u002Fapi-reference.md) |\n| Diagnose missing `pipeline.constants` or `flamingo` import | [troubleshooting](references\u002Ftroubleshooting.md#known-checkout-import-defects) |\n| Choose `fp16`, `bf16`, `int8`, `int4`, or `fp32` | [serving topology](references\u002Fserving-topology.md#worker-model-loading-choices) |\n\n## Safety boundary\n\nServing launches long-running processes, opens network ports, can download or load large checkpoints, and may allocate multiple GPUs. Do not start controller, worker, Gradio, or Flask services unless the user supplies the model\u002Fcheckpoint, host\u002Fport policy, GPU budget, and explicit permission to launch them.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fotter\u002Fsub-skills\u002Fserving",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":25},[35,38,41],{"tool":36,"command":37},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill serving",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill serving",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill serving","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fotter\u002Fsub-skills\u002Fserving\u002FSKILL.md",[46,52,56,60,66],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fapi-reference.md","REFERENCE","参考文档",3938,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fotter\u002Fsub-skills\u002Fserving\u002Freferences\u002Fapi-reference.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fserving-topology.md",5940,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fotter\u002Fsub-skills\u002Fserving\u002Freferences\u002Fserving-topology.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Ftroubleshooting.md",5637,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fotter\u002Fsub-skills\u002Fserving\u002Freferences\u002Ftroubleshooting.md",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Fbuild_serving_commands.py","SCRIPT","脚本",5715,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fotter\u002Fsub-skills\u002Fserving\u002Fscripts\u002Fbuild_serving_commands.py",{"path":67,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Fcheck_serving_imports.py",4670,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fotter\u002Fsub-skills\u002Fserving\u002Fscripts\u002Fcheck_serving_imports.py",[71,79,86,93,100,107],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":18},"01M799NYSH1R3RVAHSM2D88Y84","passnet-triton-opt","Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block\u002Fgrid\u002Fwarp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-triton-opt\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":18},"01M799NS5APEC0N1FZ7XZVW6BN","passnet-solve","END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-solve\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":18},"01M799NNY9BKSM21V5R7QVTBJX","passnet-skill","PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under .\u002Fpass_dir\u002F, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-skill\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":18},"01M799NHH6NP7Z1RK77KGXAN6S","passnet-pattern-fusion","Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()\u002Freplacement_args()\u002Freplacement_func() files, when a pass \"failed to match\", or when deciding how to fuse multiple kernels\u002Fops.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-pattern-fusion\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":18},"01M799ND2J4WNC2PGAZ0A06NDF","passnet-orchestrate","Round\u002Fbatch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep\u002Frevert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-orchestrate\u002FSKILL.md",[],[],{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":18},"01M799N8SBTMY02ZDG2AZF5ZWE","passnet-feedback","Fast, deterministic feedback for PassNet work: pre-flight pattern\u002Fmatch verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-feedback\u002FSKILL.md",[],[]]