[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7972MY654ESDP68EQVSAZ5Y":3,"skill-same:01M7972MY654ESDP68EQVSAZ5Y":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},"01M7972MY654ESDP68EQVSAZ5Y","scalar-quantizers",null,"Operate FSQ, FSP, ResidualFSQ, and GroupedResidualFSQ scalar quantizers in vector-quantize-pytorch.","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\u002Fvector-quantize-pytorch\u002Fsub-skills\u002Fscalar-quantizers\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: scalar-quantizers\ndescription: \"Operate FSQ, FSP, ResidualFSQ, and GroupedResidualFSQ scalar\n  quantizers in vector-quantize-pytorch.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Scalar Quantizers\n\nUse this sub-skill when a task needs scalar discretization in `vector-quantize-pytorch`: finite scalar quantization, finite scalar perturbation, residual scalar quantizers, grouped residual scalar quantizers, index roundtrips, tensor-layout decisions, or scalar-quantizer troubleshooting.\n\n## Route here for\n\n- `FSQ` setup with `levels`, `dim`, `num_codebooks`, `return_indices`, `channel_first`, `preserve_symmetry`, `bound_hard_clamp`, `orthogonal_rotation`, projections, and index conversion.\n- `FSP` setup with `levels`, `dim`, `channel_first`, `act_name`, `quantize_rate`, `need_inv_act`, `vector_norm`, four-value return tuples, stochastic training perturbation, and eval-time roundtrips.\n- `ResidualFSQ` and `GroupedResidualFSQ` for residual stacks, grouped feature splits, `num_quantizers`, residual reconstruction from indices, `return_all_codes`, and quantize-dropout caveats.\n- Debugging shape, dtype, projection, activation, norm, and exact-vs-allclose reconstruction issues in scalar quantizers.\n\n## Route elsewhere\n\n- Use the top-level skill to choose package installation and overall routing.\n- Use `..\u002Fvector-quantization\u002F` for learned codebook `VectorQuantize`, `RandomProjectionQuantizer`, codebook EMA, masks, and top-k\u002Fmanual EMA updates.\n- Use `..\u002Fresidual-quantizers\u002F` for `ResidualVQ` and `GroupedResidualVQ` learned-codebook residual workflows.\n- Use `..\u002Flookup-free-and-latent\u002F` for `LFQ`, `ResidualLFQ`, `GroupedResidualLFQ`, `LatentQuantize`, binary entropy losses, and lookup-free\u002Flatent quantization.\n- Use `..\u002Fsim-and-hierarchical\u002F` for `SimVQ`, `ResidualSimVQ`, and `HierarchicalVQ`.\n\n## Required references\n\nRead these bundled references before implementing or debugging a scalar workflow:\n\n1. [`references\u002Fapi-reference.md`](references\u002Fapi-reference.md) for constructor signatures, return tuples, shape contracts, index helpers, projections, and dtype behavior.\n2. [`references\u002Fworkflows.md`](references\u002Fworkflows.md) for safe FSQ\u002FFSP\u002Fresidual recipes and code patterns.\n3. [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) for common errors, unsupported settings, roundtrip caveats, and precision\u002Flayout fixes.\n\n## Safe smoke helper\n\nRun the bundled helper when you need a quick CPU sanity check of the installed package and the scalar APIs:\n\n```bash\npython scripts\u002Fsmoke_scalar_quantizers.py --help\npython scripts\u002Fsmoke_scalar_quantizers.py\n```\n\nThe helper uses small random tensors only. It does not download datasets, train MNIST models, or depend on any source tree.\n\n## Operating cautions\n\n- FSQ returns exactly two values: `(quantized, indices)`. If `return_indices=False`, the second value is `None` and index roundtrip helpers are unavailable for that instance.\n- FSP returns exactly four values: `(quantized, indices, norm_loss, other_info)`.\n- Prefer eval mode and `torch.allclose` for reconstruction checks that involve FSP, projections, autocast, or low precision. Exact equality is reliable only for the narrow deterministic cases called out in the API reference.\n- For image-like tensors, confirm whether the class expects channel-first handling. FSQ treats 4D+ inputs as channel-first feature maps; FSP requires `channel_first=True` for NCHW-style inputs.\n","# Scalar Quantizers\n\nUse this sub-skill when a task needs scalar discretization in `vector-quantize-pytorch`: finite scalar quantization, finite scalar perturbation, residual scalar quantizers, grouped residual scalar quantizers, index roundtrips, tensor-layout decisions, or scalar-quantizer troubleshooting.\n\n## Route here for\n\n- `FSQ` setup with `levels`, `dim`, `num_codebooks`, `return_indices`, `channel_first`, `preserve_symmetry`, `bound_hard_clamp`, `orthogonal_rotation`, projections, and index conversion.\n- `FSP` setup with `levels`, `dim`, `channel_first`, `act_name`, `quantize_rate`, `need_inv_act`, `vector_norm`, four-value return tuples, stochastic training perturbation, and eval-time roundtrips.\n- `ResidualFSQ` and `GroupedResidualFSQ` for residual stacks, grouped feature splits, `num_quantizers`, residual reconstruction from indices, `return_all_codes`, and quantize-dropout caveats.\n- Debugging shape, dtype, projection, activation, norm, and exact-vs-allclose reconstruction issues in scalar quantizers.\n\n## Route elsewhere\n\n- Use the top-level skill to choose package installation and overall routing.\n- Use `..\u002Fvector-quantization\u002F` for learned codebook `VectorQuantize`, `RandomProjectionQuantizer`, codebook EMA, masks, and top-k\u002Fmanual EMA updates.\n- Use `..\u002Fresidual-quantizers\u002F` for `ResidualVQ` and `GroupedResidualVQ` learned-codebook residual workflows.\n- Use `..\u002Flookup-free-and-latent\u002F` for `LFQ`, `ResidualLFQ`, `GroupedResidualLFQ`, `LatentQuantize`, binary entropy losses, and lookup-free\u002Flatent quantization.\n- Use `..\u002Fsim-and-hierarchical\u002F` for `SimVQ`, `ResidualSimVQ`, and `HierarchicalVQ`.\n\n## Required references\n\nRead these bundled references before implementing or debugging a scalar workflow:\n\n1. [`references\u002Fapi-reference.md`](references\u002Fapi-reference.md) for constructor signatures, return tuples, shape contracts, index helpers, projections, and dtype behavior.\n2. [`references\u002Fworkflows.md`](references\u002Fworkflows.md) for safe FSQ\u002FFSP\u002Fresidual recipes and code patterns.\n3. [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) for common errors, unsupported settings, roundtrip caveats, and precision\u002Flayout fixes.\n\n## Safe smoke helper\n\nRun the bundled helper when you need a quick CPU sanity check of the installed package and the scalar APIs:\n\n```bash\npython scripts\u002Fsmoke_scalar_quantizers.py --help\npython scripts\u002Fsmoke_scalar_quantizers.py\n```\n\nThe helper uses small random tensors only. It does not download datasets, train MNIST models, or depend on any source tree.\n\n## Operating cautions\n\n- FSQ returns exactly two values: `(quantized, indices)`. If `return_indices=False`, the second value is `None` and index roundtrip helpers are unavailable for that instance.\n- FSP returns exactly four values: `(quantized, indices, norm_loss, other_info)`.\n- Prefer eval mode and `torch.allclose` for reconstruction checks that involve FSP, projections, autocast, or low precision. Exact equality is reliable only for the narrow deterministic cases called out in the API reference.\n- For image-like tensors, confirm whether the class expects channel-first handling. FSQ treats 4D+ inputs as channel-first feature maps; FSP requires `channel_first=True` for NCHW-style inputs.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fvector-quantize-pytorch\u002Fsub-skills\u002Fscalar-quantizers",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 scalar-quantizers",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill scalar-quantizers",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill scalar-quantizers","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fvector-quantize-pytorch\u002Fsub-skills\u002Fscalar-quantizers\u002FSKILL.md",[46,52,56,60],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fapi-reference.md","REFERENCE","参考文档",11165,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fvector-quantize-pytorch\u002Fsub-skills\u002Fscalar-quantizers\u002Freferences\u002Fapi-reference.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Ftroubleshooting.md",9176,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fvector-quantize-pytorch\u002Fsub-skills\u002Fscalar-quantizers\u002Freferences\u002Ftroubleshooting.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fworkflows.md",7828,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fvector-quantize-pytorch\u002Fsub-skills\u002Fscalar-quantizers\u002Freferences\u002Fworkflows.md",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Fsmoke_scalar_quantizers.py","SCRIPT","脚本",10653,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fvector-quantize-pytorch\u002Fsub-skills\u002Fscalar-quantizers\u002Fscripts\u002Fsmoke_scalar_quantizers.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",[],[]]