[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78Y0TAMWWZ4C1VPVB46FCK3":3,"skill-same:01M78Y0TAMWWZ4C1VPVB46FCK3":60},{"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},"01M78Y0TAMWWZ4C1VPVB46FCK3","moe",null,"Routes Hivemind remote expert and mixture-of-experts workflows, including server setup, custom expert registration, and client-side expert routing.","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\u002Fhivemind\u002Fsub-skills\u002Fmoe\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: moe\ndescription: \"Routes Hivemind remote expert and mixture-of-experts workflows,\n  including server setup, custom expert registration, and client-side expert\n  routing.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Mixture of Experts\n\nUse this route when the task is about `hivemind.moe.Server`, `ModuleBackend`, `RemoteExpert`, `RemoteMixtureOfExperts`, `RemoteSwitchMixtureOfExperts`, custom expert registration, or the `hivemind-server` command.\n\n## Include\n\n- Hosting experts with `hivemind.moe.server.Server` or `background_server`.\n- Remote expert clients with `RemoteExpert` and the MoE routing layers.\n- Declaring and discovering experts with `declare_experts` and `get_experts`.\n- Custom expert classes via `register_expert_class` and `custom_module_path`.\n- Checkpointing and backend scheduling behavior in `ModuleBackend`.\n- The `hivemind-server` console command.\n\n## Exclude\n\n- DHT bootstrap and network reachability debugging; route that to `dht`.\n- Optimizer wrapping, tensor averaging, and ALBERT training; route those to `collaborative-training`.\n- Benchmarks and throughput experiments.\n\n## Start here\n\n1. Read [`references\u002Fapi-reference.md`](references\u002Fapi-reference.md) for the verified server\u002Fclient signatures.\n2. Read [`references\u002Fworkflows.md`](references\u002Fworkflows.md) for the standard server, client, and custom-expert flows.\n3. Read [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) when the server cannot publish experts, clients cannot find experts, or a custom module fails to load.\n4. Run [`..\u002F..\u002Fscripts\u002Fcheck_install.py`](..\u002F..\u002Fscripts\u002Fcheck_install.py) from the generated skill tree to confirm the installed package and CLI entry points.\n\n## What to remember\n\n- `hivemind-server` is the package command for serving experts.\n- `background_server(...)` is the fastest way to spin up a temporary expert host in tests or small demos.\n- `client_mode` matters when a client can dial out but should not accept inbound connections.\n- `custom_module_path` lets the server load extra expert definitions from a Python file.\n- `Server.create(...)` accepts either explicit expert UIDs or generated patterns.\n- On CUDA-capable hosts, the server may default to GPU execution unless you request `--device cpu`.\n\n## Good follow-up questions\n\n- \"How do I host experts and connect to them remotely?\"\n- \"How do I register a custom expert class?\"\n- \"How do I fetch experts from the DHT?\"\n- \"Why does `hivemind-server` say an expert is missing?\"\n- \"How do I checkpoint expert state?\"\n","# Mixture of Experts\n\nUse this route when the task is about `hivemind.moe.Server`, `ModuleBackend`, `RemoteExpert`, `RemoteMixtureOfExperts`, `RemoteSwitchMixtureOfExperts`, custom expert registration, or the `hivemind-server` command.\n\n## Include\n\n- Hosting experts with `hivemind.moe.server.Server` or `background_server`.\n- Remote expert clients with `RemoteExpert` and the MoE routing layers.\n- Declaring and discovering experts with `declare_experts` and `get_experts`.\n- Custom expert classes via `register_expert_class` and `custom_module_path`.\n- Checkpointing and backend scheduling behavior in `ModuleBackend`.\n- The `hivemind-server` console command.\n\n## Exclude\n\n- DHT bootstrap and network reachability debugging; route that to `dht`.\n- Optimizer wrapping, tensor averaging, and ALBERT training; route those to `collaborative-training`.\n- Benchmarks and throughput experiments.\n\n## Start here\n\n1. Read [`references\u002Fapi-reference.md`](references\u002Fapi-reference.md) for the verified server\u002Fclient signatures.\n2. Read [`references\u002Fworkflows.md`](references\u002Fworkflows.md) for the standard server, client, and custom-expert flows.\n3. Read [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) when the server cannot publish experts, clients cannot find experts, or a custom module fails to load.\n4. Run [`..\u002F..\u002Fscripts\u002Fcheck_install.py`](..\u002F..\u002Fscripts\u002Fcheck_install.py) from the generated skill tree to confirm the installed package and CLI entry points.\n\n## What to remember\n\n- `hivemind-server` is the package command for serving experts.\n- `background_server(...)` is the fastest way to spin up a temporary expert host in tests or small demos.\n- `client_mode` matters when a client can dial out but should not accept inbound connections.\n- `custom_module_path` lets the server load extra expert definitions from a Python file.\n- `Server.create(...)` accepts either explicit expert UIDs or generated patterns.\n- On CUDA-capable hosts, the server may default to GPU execution unless you request `--device cpu`.\n\n## Good follow-up questions\n\n- \"How do I host experts and connect to them remotely?\"\n- \"How do I register a custom expert class?\"\n- \"How do I fetch experts from the DHT?\"\n- \"Why does `hivemind-server` say an expert is missing?\"\n- \"How do I checkpoint expert state?\"\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fhivemind\u002Fsub-skills\u002Fmoe",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 moe",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill moe",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill moe","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fhivemind\u002Fsub-skills\u002Fmoe\u002FSKILL.md",[46,52,56],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fapi-reference.md","REFERENCE","参考文档",4333,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fhivemind\u002Fsub-skills\u002Fmoe\u002Freferences\u002Fapi-reference.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Ftroubleshooting.md",3900,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fhivemind\u002Fsub-skills\u002Fmoe\u002Freferences\u002Ftroubleshooting.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fworkflows.md",3358,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fhivemind\u002Fsub-skills\u002Fmoe\u002Freferences\u002Fworkflows.md",[61,69,76,83,90,97],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":65,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"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":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":65,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"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":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":65,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"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":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":65,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"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":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":65,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"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":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":65,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"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",[],[]]