[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M797TPCP6WT0AYBQVCS0H4PX":3,"skill-same:01M797TPCP6WT0AYBQVCS0H4PX":58},{"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":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M797TPCP6WT0AYBQVCS0H4PX","dependency_group_pruning",null,"Aggregate LoRAPrune element importances into structured groups and create deterministic channel or head pruning masks.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fadaptive-pruning\u002Fskill\u002Flora_prune\u002Fdependency_group_pruning\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: dependency_group_pruning\ndescription: Aggregate LoRAPrune element importances into structured groups and create deterministic channel or head pruning masks.\n---\n\n# Dependency Group Pruning\n\nUse this skill after a criterion has produced elementwise importance and before applying LoRAPrune masks. It is for structured row, column, channel, or head pruning, not unstructured element sparsity.\n\n## Inputs\n\n- An importance matrix or tensor slice.\n- A grouping convention, such as row groups for output channels or column groups for input channels.\n- A prune count or equivalent target sparsity converted to a group count.\n\n## Outputs\n\n- Group importance scores computed by summing member weights.\n- A binary group mask: `1` keeps a group and `0` prunes it.\n- A broadcastable element mask for the represented weight matrix.\n\n## Workflow\n\n1. Validate the importance shape and group specification.\n2. Accumulate group scores following LoRAPrune Eq. 4.\n3. Sort scores ascending with stable index tie-breaking.\n4. Mark the lowest-scoring groups as pruned according to the requested sparsity.\n5. Broadcast the group mask to the element shape for the masked forward pass.\n\n## Validation\n\nRun the skill tree validator with tests. The deterministic tests cover row grouping, column grouping, broadcast masks, and stable tie handling.\n\n```bash\npython \u002Fshare\u002Fproject\u002Fyuyang\u002Fworkspace\u002FPaper2Skills\u002FDistiller\u002Fskills\u002Fmodule-to-skill\u002Fscripts\u002Fvalidate_skill_tree.py \u003Cthis_skill_dir> --run-tests\n```\n\n## Limitations\n\nThe supplied script implements row and column groups for reduced recovery. Full transformer pruning should map attention heads and MLP channels into equivalent groups while preserving this contract: group scores are accumulated before thresholding, and masks prune whole structures.\n","# Dependency Group Pruning\n\nUse this skill after a criterion has produced elementwise importance and before applying LoRAPrune masks. It is for structured row, column, channel, or head pruning, not unstructured element sparsity.\n\n## Inputs\n\n- An importance matrix or tensor slice.\n- A grouping convention, such as row groups for output channels or column groups for input channels.\n- A prune count or equivalent target sparsity converted to a group count.\n\n## Outputs\n\n- Group importance scores computed by summing member weights.\n- A binary group mask: `1` keeps a group and `0` prunes it.\n- A broadcastable element mask for the represented weight matrix.\n\n## Workflow\n\n1. Validate the importance shape and group specification.\n2. Accumulate group scores following LoRAPrune Eq. 4.\n3. Sort scores ascending with stable index tie-breaking.\n4. Mark the lowest-scoring groups as pruned according to the requested sparsity.\n5. Broadcast the group mask to the element shape for the masked forward pass.\n\n## Validation\n\nRun the skill tree validator with tests. The deterministic tests cover row grouping, column grouping, broadcast masks, and stable tie handling.\n\n```bash\npython \u002Fshare\u002Fproject\u002Fyuyang\u002Fworkspace\u002FPaper2Skills\u002FDistiller\u002Fskills\u002Fmodule-to-skill\u002Fscripts\u002Fvalidate_skill_tree.py \u003Cthis_skill_dir> --run-tests\n```\n\n## Limitations\n\nThe supplied script implements row and column groups for reduced recovery. Full transformer pruning should map attention heads and MLP channels into equivalent groups while preserving this contract: group scores are accumulated before thresholding, and masks prune whole structures.\n",{"name":5,"description":7},"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fadaptive-pruning\u002Fskill\u002Flora_prune\u002Fdependency_group_pruning",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill dependency_group_pruning",{"tool":36,"command":37},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill dependency_group_pruning",{"tool":39,"command":40},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill dependency_group_pruning","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fadaptive-pruning\u002Fskill\u002Flora_prune\u002Fdependency_group_pruning\u002FSKILL.md",true,[44,50,54],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"scripts\u002Fgroup_pruning.py","SCRIPT","脚本",2638,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fadaptive-pruning\u002Fskill\u002Flora_prune\u002Fdependency_group_pruning\u002Fscripts\u002Fgroup_pruning.py",{"path":51,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":52,"sourceHtmlUrl":53},"tests\u002Ftest_group_pruning.py",782,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fadaptive-pruning\u002Fskill\u002Flora_prune\u002Fdependency_group_pruning\u002Ftests\u002Ftest_group_pruning.py",{"path":55,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":56,"sourceHtmlUrl":57},"tests\u002Ftest_invalid_prune_count.py",286,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fadaptive-pruning\u002Fskill\u002Flora_prune\u002Fdependency_group_pruning\u002Ftests\u002Ftest_invalid_prune_count.py",[59,66,73,80,87,94],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"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.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-triton-opt\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"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":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"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":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"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":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"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":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"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",[],[]]