[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M790CRVSAZFGVC3HT2YKPFG8":3,"skill-same:01M790CRVSAZFGVC3HT2YKPFG8":66},{"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},"01M790CRVSAZFGVC3HT2YKPFG8","expert-cache",null,"Debug and extend mixtral-offloading's MoE expert cache, storage wrapper, and sparse routing internals.","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\u002Fmixtral-offloading\u002Fsub-skills\u002Fexpert-cache\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: expert-cache\ndescription: \"Debug and extend mixtral-offloading's MoE expert cache, storage\n  wrapper, and sparse routing internals.\"\nmetadata:\n  disco-role: operating\ndisable-model-invocation: true\nlicense: MIT\n---\n\n# Expert Cache\n\nUse this sub-skill when the task is about expert offloading internals rather\nthan simply running the demo: `ExpertCache`, `MixtralExpertWrapper`,\n`SparseMoeWrapper`, expert UIDs, LRU eviction groups, pinned offload storage,\nor cache-capacity errors.\n\n## Read this when\n\n- The user sees `Cache is full`, `No evictable experts`, `already loading\n  experts`, duplicate expert UID assertions, or eviction-group assertions.\n- The task is to change offloading policy, add prefetching, debug storage\n  movement, or inspect sparse MoE routing.\n- The user wants to understand how `offload_per_layer` becomes `main_size` and\n  `offload_size` inside `ExpertCache`.\n\n## Route map\n\n1. Read [references\u002Fexpert-cache-api.md](references\u002Fexpert-cache-api.md) for\n   `ExpertInfo`, `EvictionGroupInfo`, `ExpertCache`, and method invariants.\n2. Read [references\u002Fstorage-and-routing.md](references\u002Fstorage-and-routing.md)\n   for `MixtralExpertWrapper` storage replacement and `SparseMoeWrapper.forward`\n   routing flow.\n3. Use [scripts\u002Finspect_cache_plan.py](scripts\u002Finspect_cache_plan.py) to compute\n   cache capacities and example expert UIDs without loading model weights.\n4. Read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) for\n   capacity, reentrancy, storage, pinned-memory, and routing-shape failures.\n\n## What this sub-skill owns\n\n- Expert-cache capacity and eviction invariants.\n- Expert UID layout and eviction-group behavior.\n- Storage wrapping and state-dict storage hooks.\n- Sparse MoE top-k routing through cached experts.\n\n## What to route elsewhere\n\n- Use [..\u002Finference-workflow\u002FSKILL.md](..\u002Finference-workflow\u002FSKILL.md) for full\n  model construction, generation, and offload config selection.\n- Use [..\u002Fquantization-kernels\u002FSKILL.md](..\u002Fquantization-kernels\u002FSKILL.md) for\n  HQQ quantized MLP layers, packing, and Triton kernel failures.\n\n## Safe verification\n\nMost cache internals require real `MixtralExpertWrapper` objects backed by\nCUDA `UntypedStorage`. For safe planning, use the bundled script and source\u002FAPI\nreasoning. Do not construct the full cache with dummy objects unless their\nstorage type, size, and device match the expected wrapper invariants.\n","# Expert Cache\n\nUse this sub-skill when the task is about expert offloading internals rather\nthan simply running the demo: `ExpertCache`, `MixtralExpertWrapper`,\n`SparseMoeWrapper`, expert UIDs, LRU eviction groups, pinned offload storage,\nor cache-capacity errors.\n\n## Read this when\n\n- The user sees `Cache is full`, `No evictable experts`, `already loading\n  experts`, duplicate expert UID assertions, or eviction-group assertions.\n- The task is to change offloading policy, add prefetching, debug storage\n  movement, or inspect sparse MoE routing.\n- The user wants to understand how `offload_per_layer` becomes `main_size` and\n  `offload_size` inside `ExpertCache`.\n\n## Route map\n\n1. Read [references\u002Fexpert-cache-api.md](references\u002Fexpert-cache-api.md) for\n   `ExpertInfo`, `EvictionGroupInfo`, `ExpertCache`, and method invariants.\n2. Read [references\u002Fstorage-and-routing.md](references\u002Fstorage-and-routing.md)\n   for `MixtralExpertWrapper` storage replacement and `SparseMoeWrapper.forward`\n   routing flow.\n3. Use [scripts\u002Finspect_cache_plan.py](scripts\u002Finspect_cache_plan.py) to compute\n   cache capacities and example expert UIDs without loading model weights.\n4. Read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) for\n   capacity, reentrancy, storage, pinned-memory, and routing-shape failures.\n\n## What this sub-skill owns\n\n- Expert-cache capacity and eviction invariants.\n- Expert UID layout and eviction-group behavior.\n- Storage wrapping and state-dict storage hooks.\n- Sparse MoE top-k routing through cached experts.\n\n## What to route elsewhere\n\n- Use [..\u002Finference-workflow\u002FSKILL.md](..\u002Finference-workflow\u002FSKILL.md) for full\n  model construction, generation, and offload config selection.\n- Use [..\u002Fquantization-kernels\u002FSKILL.md](..\u002Fquantization-kernels\u002FSKILL.md) for\n  HQQ quantized MLP layers, packing, and Triton kernel failures.\n\n## Safe verification\n\nMost cache internals require real `MixtralExpertWrapper` objects backed by\nCUDA `UntypedStorage`. For safe planning, use the bundled script and source\u002FAPI\nreasoning. Do not construct the full cache with dummy objects unless their\nstorage type, size, and device match the expected wrapper invariants.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fmixtral-offloading\u002Fsub-skills\u002Fexpert-cache",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 expert-cache",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill expert-cache",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill expert-cache","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmixtral-offloading\u002Fsub-skills\u002Fexpert-cache\u002FSKILL.md",[46,52,56,60],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fexpert-cache-api.md","REFERENCE","参考文档",2934,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmixtral-offloading\u002Fsub-skills\u002Fexpert-cache\u002Freferences\u002Fexpert-cache-api.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fstorage-and-routing.md",2393,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmixtral-offloading\u002Fsub-skills\u002Fexpert-cache\u002Freferences\u002Fstorage-and-routing.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Ftroubleshooting.md",2292,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmixtral-offloading\u002Fsub-skills\u002Fexpert-cache\u002Freferences\u002Ftroubleshooting.md",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Finspect_cache_plan.py","SCRIPT","脚本",2463,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fmixtral-offloading\u002Fsub-skills\u002Fexpert-cache\u002Fscripts\u002Finspect_cache_plan.py",[67,75,82,89,96,103],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"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":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"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":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"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":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"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":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"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":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"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",[],[]]