[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M793N4T3KZ2BWAA2G19V7GCD":3,"skill-same:01M793N4T3KZ2BWAA2G19V7GCD":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},"01M793N4T3KZ2BWAA2G19V7GCD","index-batching",null,"Guides memory-efficient PyTorch Geometric Temporal index-batching, GPU preprocessing flags, loader return tuples, and optional Dask-DDP training.","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\u002Fpytorch-geometric-temporal\u002Fsub-skills\u002Findex-batching\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: index-batching\ndescription: \"Guides memory-efficient PyTorch Geometric Temporal index-batching,\n  GPU preprocessing flags, loader return tuples, and optional Dask-DDP\n  training.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Index Batching\n\nUse this sub-skill when the task asks about PyTorch Geometric Temporal index-batching, memory-efficient temporal mini-batches, `get_index_dataset`, `IndexDataset`, `allGPU`, `dask_batching`, `world_size`\u002F`ddp_rank`, Dask-DDP, or errors caused by missing `index=True`.\n\n## Route here when\n\n- The user wants a `DataLoader` that yields sequence windows instead of a full temporal signal iterator.\n- The user is adapting Chickenpox, WindmillLarge, METR-LA, PeMS-Bay, PeMS-All-LA, or full PeMS to index batching.\n- The question is about 5-tuple versus 7-tuple `get_index_dataset` returns, normalization statistics, or batch tensor shape.\n- The user needs to decide between CPU preprocessing (`allGPU=-1`), GPU index preprocessing (`allGPU=\u003Cdevice_id>`), or optional Dask-DDP distributed training.\n- The error mentions `get_index_dataset requires 'index=True'`, missing `dask`\u002F`pandas`\u002F`tables`, CUDA not available, or `DistributedSampler` rank\u002Freplica problems.\n\n## Do not handle here\n\n- Ordinary temporal signal iterators such as `StaticGraphTemporalSignal`, dynamic graph signals, hetero signals, slicing, or `temporal_signal_split`; route those to the temporal-signals sub-skill.\n- Ordinary `get_dataset()` loader workflows, download\u002Fcache planning, and non-index dataset catalogs; route those to the dataset-loaders sub-skill.\n- Model architecture selection and recurrent\u002Fattention layer internals beyond the batched output shape needed to connect an index batch to a model loop; route those to the model sub-skills.\n- Real multi-node cluster execution or scheduler launch scripts as a required verification step; this sub-skill only provides reference patterns and prerequisites.\n\n## First facts to apply\n\n- `IndexDataset` is not exported from `torch_geometric_temporal.signal`; import it explicitly with:\n\n  ```python\n  from torch_geometric_temporal.signal.index_dataset import IndexDataset\n  ```\n\n- Loader index batching is opt-in. Instantiate supported loaders with `index=True` before calling `get_index_dataset(...)`.\n- `IndexDataset(indices, data, horizon, lazy=False, gpu=False)` stores start indices and returns `(X_window, y_window)`, where both windows have length `horizon`\u002F`lags` along time.\n- Batches yielded by built-in index dataloaders have sequence-to-sequence layout close to `[batch, lags, num_nodes, num_features]` before any model-specific permutation.\n- Chickenpox returns a 5-tuple; WindmillLarge, METR-LA, PeMS-Bay, PeMS-All-LA, and PeMS return a 7-tuple with normalization statistics.\n\n## What to read or run\n\n1. Read [workflows.md](references\u002Fworkflows.md) for CPU\u002FGPU index-batching setup, supported loader return formats, tuple unpacking, normalization statistics, ratio\u002Flags behavior, and model-loop shape notes.\n2. Read [distributed-ddp.md](references\u002Fdistributed-ddp.md) only when the user asks for Dask-DDP, multi-GPU, multi-node, `world_size`, `ddp_rank`, `DistributedSampler`, or scheduler-file behavior.\n3. Read [troubleshooting.md](references\u002Ftroubleshooting.md) when an index-batching call fails or when optional dependencies, CUDA, Dask, ranks, tuple lengths, downloads, or empty splits are involved.\n4. Run or adapt [index_batching_smoke.py](scripts\u002Findex_batching_smoke.py) for a deterministic no-network synthetic `IndexDataset` sanity check.\n\n## Minimal safe workflow\n\n```python\nfrom torch_geometric_temporal.dataset import PemsBayDatasetLoader\n\nloader = PemsBayDatasetLoader(index=True)\ntrain_loader, val_loader, test_loader, edge_index, edge_weight, mean, std = (\n    loader.get_index_dataset(lags=12, batch_size=64, shuffle=True, allGPU=-1)\n)\n\nfor X_batch, y_batch in train_loader:\n    # CPU preprocessing path: move tensors to the model device inside the loop.\n    # X_batch\u002Fy_batch are sequence windows, typically [B, T, N, F].\n    pass\n```\n\nFor Chickenpox, unpack five values instead:\n\n```python\ntrain_loader, val_loader, test_loader, edge_index, edge_weight = (\n    ChickenpoxDatasetLoader(index=True).get_index_dataset(lags=4, batch_size=4)\n)\n```\n\nIf the task requires exact loader-specific shapes, DDP behavior, or de-normalization, open the references instead of expanding this router.\n","# Index Batching\n\nUse this sub-skill when the task asks about PyTorch Geometric Temporal index-batching, memory-efficient temporal mini-batches, `get_index_dataset`, `IndexDataset`, `allGPU`, `dask_batching`, `world_size`\u002F`ddp_rank`, Dask-DDP, or errors caused by missing `index=True`.\n\n## Route here when\n\n- The user wants a `DataLoader` that yields sequence windows instead of a full temporal signal iterator.\n- The user is adapting Chickenpox, WindmillLarge, METR-LA, PeMS-Bay, PeMS-All-LA, or full PeMS to index batching.\n- The question is about 5-tuple versus 7-tuple `get_index_dataset` returns, normalization statistics, or batch tensor shape.\n- The user needs to decide between CPU preprocessing (`allGPU=-1`), GPU index preprocessing (`allGPU=\u003Cdevice_id>`), or optional Dask-DDP distributed training.\n- The error mentions `get_index_dataset requires 'index=True'`, missing `dask`\u002F`pandas`\u002F`tables`, CUDA not available, or `DistributedSampler` rank\u002Freplica problems.\n\n## Do not handle here\n\n- Ordinary temporal signal iterators such as `StaticGraphTemporalSignal`, dynamic graph signals, hetero signals, slicing, or `temporal_signal_split`; route those to the temporal-signals sub-skill.\n- Ordinary `get_dataset()` loader workflows, download\u002Fcache planning, and non-index dataset catalogs; route those to the dataset-loaders sub-skill.\n- Model architecture selection and recurrent\u002Fattention layer internals beyond the batched output shape needed to connect an index batch to a model loop; route those to the model sub-skills.\n- Real multi-node cluster execution or scheduler launch scripts as a required verification step; this sub-skill only provides reference patterns and prerequisites.\n\n## First facts to apply\n\n- `IndexDataset` is not exported from `torch_geometric_temporal.signal`; import it explicitly with:\n\n  ```python\n  from torch_geometric_temporal.signal.index_dataset import IndexDataset\n  ```\n\n- Loader index batching is opt-in. Instantiate supported loaders with `index=True` before calling `get_index_dataset(...)`.\n- `IndexDataset(indices, data, horizon, lazy=False, gpu=False)` stores start indices and returns `(X_window, y_window)`, where both windows have length `horizon`\u002F`lags` along time.\n- Batches yielded by built-in index dataloaders have sequence-to-sequence layout close to `[batch, lags, num_nodes, num_features]` before any model-specific permutation.\n- Chickenpox returns a 5-tuple; WindmillLarge, METR-LA, PeMS-Bay, PeMS-All-LA, and PeMS return a 7-tuple with normalization statistics.\n\n## What to read or run\n\n1. Read [workflows.md](references\u002Fworkflows.md) for CPU\u002FGPU index-batching setup, supported loader return formats, tuple unpacking, normalization statistics, ratio\u002Flags behavior, and model-loop shape notes.\n2. Read [distributed-ddp.md](references\u002Fdistributed-ddp.md) only when the user asks for Dask-DDP, multi-GPU, multi-node, `world_size`, `ddp_rank`, `DistributedSampler`, or scheduler-file behavior.\n3. Read [troubleshooting.md](references\u002Ftroubleshooting.md) when an index-batching call fails or when optional dependencies, CUDA, Dask, ranks, tuple lengths, downloads, or empty splits are involved.\n4. Run or adapt [index_batching_smoke.py](scripts\u002Findex_batching_smoke.py) for a deterministic no-network synthetic `IndexDataset` sanity check.\n\n## Minimal safe workflow\n\n```python\nfrom torch_geometric_temporal.dataset import PemsBayDatasetLoader\n\nloader = PemsBayDatasetLoader(index=True)\ntrain_loader, val_loader, test_loader, edge_index, edge_weight, mean, std = (\n    loader.get_index_dataset(lags=12, batch_size=64, shuffle=True, allGPU=-1)\n)\n\nfor X_batch, y_batch in train_loader:\n    # CPU preprocessing path: move tensors to the model device inside the loop.\n    # X_batch\u002Fy_batch are sequence windows, typically [B, T, N, F].\n    pass\n```\n\nFor Chickenpox, unpack five values instead:\n\n```python\ntrain_loader, val_loader, test_loader, edge_index, edge_weight = (\n    ChickenpoxDatasetLoader(index=True).get_index_dataset(lags=4, batch_size=4)\n)\n```\n\nIf the task requires exact loader-specific shapes, DDP behavior, or de-normalization, open the references instead of expanding this router.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fpytorch-geometric-temporal\u002Fsub-skills\u002Findex-batching",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 index-batching",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill index-batching",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill index-batching","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpytorch-geometric-temporal\u002Fsub-skills\u002Findex-batching\u002FSKILL.md",[46,52,56,60],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fdistributed-ddp.md","REFERENCE","参考文档",6791,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpytorch-geometric-temporal\u002Fsub-skills\u002Findex-batching\u002Freferences\u002Fdistributed-ddp.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Ftroubleshooting.md",6177,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpytorch-geometric-temporal\u002Fsub-skills\u002Findex-batching\u002Freferences\u002Ftroubleshooting.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fworkflows.md",9643,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpytorch-geometric-temporal\u002Fsub-skills\u002Findex-batching\u002Freferences\u002Fworkflows.md",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Findex_batching_smoke.py","SCRIPT","脚本",8362,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpytorch-geometric-temporal\u002Fsub-skills\u002Findex-batching\u002Fscripts\u002Findex_batching_smoke.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",[],[]]