[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M796SF5KER787EF9B46CWFQ3":3,"skill-same:01M796SF5KER787EF9B46CWFQ3":67},{"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":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":46},"01M796SF5KER787EF9B46CWFQ3","s-tir-tuning",null,"Guides TVM S-TIR scheduling, transformations, dlight rules, meta-schedule tuning, builders, runners, and CPU\u002FGPU tuning decisions.","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\u002Frepositories\u002Frepo-skills\u002Ftvm\u002Fsub-skills\u002Fs-tir-tuning\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: s-tir-tuning\ndescription: \"Guides TVM S-TIR scheduling, transformations, dlight rules,\n  meta-schedule tuning, builders, runners, and CPU\u002FGPU tuning decisions.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# S-TIR Scheduling and Tuning\n\nUse this route when a task involves `tvm.s_tir.Schedule`, schedule primitives,\ntransform passes, dlight\u002Fdefault schedules, meta-schedule, `tune_tir`, or\nbounded tuning of TIR generated from Relax or TIRx.\n\n## Route\n\n1. Confirm TVM imports and the selected target is available. Use\n   [`..\u002Finstall-build\u002FSKILL.md`](..\u002Finstall-build\u002FSKILL.md) for package\u002Fbuild\n   failures.\n2. Decide whether the user needs manual scheduling, a transform pass, dlight, or\n   meta-schedule tuning.\n3. For manual schedules and debug traces, read\n   [`references\u002Fschedule-workflows.md`](references\u002Fschedule-workflows.md).\n4. For `tune_tir`, builder\u002Frunner\u002Fdatabase\u002Fcost-model decisions, or bounded\n   tuning runs, read [`references\u002Fmeta-schedule.md`](references\u002Fmeta-schedule.md).\n5. Run [`scripts\u002Fmeta_schedule_import_probe.py`](scripts\u002Fmeta_schedule_import_probe.py)\n   before a tuning run to verify the API and optional dependencies.\n6. Use [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) for\n   `ScheduleError`, invalid traces, no-candidate tuning, database, XGBoost,\n   runner\u002FRPC, and backend issues.\n\n## API anchors\n\n```python\nfrom tvm.s_tir import Schedule\nfrom tvm.s_tir import meta_schedule as ms\n\nsch = Schedule(mod, seed=None, debug_mask=\"none\", error_render_level=\"detail\", enable_check=True)\nms.tune_tir(mod, target, work_dir, max_trials_global, runner=\"local\", database=\"json\")\n```\n\n`tune_tir` returns a meta-schedule `Database`. Use tiny `max_trials_global`\nvalues for smoke checks, a disposable `work_dir`, and a CPU target unless the\nuser has explicitly prepared a GPU\u002FRPC backend.\n\n## Boundaries\n\n- Relax model import and high-level pipelines: [`..\u002Frelax-compile\u002FSKILL.md`](..\u002Frelax-compile\u002FSKILL.md).\n- TIRx tile primitives and native kernel dispatch: [`..\u002Ftirx-kernels\u002FSKILL.md`](..\u002Ftirx-kernels\u002FSKILL.md).\n- RPC tracker\u002Fserver setup for remote runners: [`..\u002Frpc-deployment\u002FSKILL.md`](..\u002Frpc-deployment\u002FSKILL.md).\n- Package\u002Ftoolchain failures: [`..\u002Finstall-build\u002FSKILL.md`](..\u002Finstall-build\u002FSKILL.md).\n","# S-TIR Scheduling and Tuning\n\nUse this route when a task involves `tvm.s_tir.Schedule`, schedule primitives,\ntransform passes, dlight\u002Fdefault schedules, meta-schedule, `tune_tir`, or\nbounded tuning of TIR generated from Relax or TIRx.\n\n## Route\n\n1. Confirm TVM imports and the selected target is available. Use\n   [`..\u002Finstall-build\u002FSKILL.md`](..\u002Finstall-build\u002FSKILL.md) for package\u002Fbuild\n   failures.\n2. Decide whether the user needs manual scheduling, a transform pass, dlight, or\n   meta-schedule tuning.\n3. For manual schedules and debug traces, read\n   [`references\u002Fschedule-workflows.md`](references\u002Fschedule-workflows.md).\n4. For `tune_tir`, builder\u002Frunner\u002Fdatabase\u002Fcost-model decisions, or bounded\n   tuning runs, read [`references\u002Fmeta-schedule.md`](references\u002Fmeta-schedule.md).\n5. Run [`scripts\u002Fmeta_schedule_import_probe.py`](scripts\u002Fmeta_schedule_import_probe.py)\n   before a tuning run to verify the API and optional dependencies.\n6. Use [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) for\n   `ScheduleError`, invalid traces, no-candidate tuning, database, XGBoost,\n   runner\u002FRPC, and backend issues.\n\n## API anchors\n\n```python\nfrom tvm.s_tir import Schedule\nfrom tvm.s_tir import meta_schedule as ms\n\nsch = Schedule(mod, seed=None, debug_mask=\"none\", error_render_level=\"detail\", enable_check=True)\nms.tune_tir(mod, target, work_dir, max_trials_global, runner=\"local\", database=\"json\")\n```\n\n`tune_tir` returns a meta-schedule `Database`. Use tiny `max_trials_global`\nvalues for smoke checks, a disposable `work_dir`, and a CPU target unless the\nuser has explicitly prepared a GPU\u002FRPC backend.\n\n## Boundaries\n\n- Relax model import and high-level pipelines: [`..\u002Frelax-compile\u002FSKILL.md`](..\u002Frelax-compile\u002FSKILL.md).\n- TIRx tile primitives and native kernel dispatch: [`..\u002Ftirx-kernels\u002FSKILL.md`](..\u002Ftirx-kernels\u002FSKILL.md).\n- RPC tracker\u002Fserver setup for remote runners: [`..\u002Frpc-deployment\u002FSKILL.md`](..\u002Frpc-deployment\u002FSKILL.md).\n- Package\u002Ftoolchain failures: [`..\u002Finstall-build\u002FSKILL.md`](..\u002Finstall-build\u002FSKILL.md).\n",{"name":5,"license":23,"metadata":24,"description":7,"disable-model-invocation":26},"Apache 2.0",{"disco-role":25},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Ftvm\u002Fsub-skills\u002Fs-tir-tuning",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":26},[36,39,42],{"tool":37,"command":38},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill s-tir-tuning",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill s-tir-tuning",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill s-tir-tuning","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftvm\u002Fsub-skills\u002Fs-tir-tuning\u002FSKILL.md",[47,53,57,61],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fmeta-schedule.md","REFERENCE","参考文档",3376,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftvm\u002Fsub-skills\u002Fs-tir-tuning\u002Freferences\u002Fmeta-schedule.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fschedule-workflows.md",2928,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftvm\u002Fsub-skills\u002Fs-tir-tuning\u002Freferences\u002Fschedule-workflows.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",2516,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftvm\u002Fsub-skills\u002Fs-tir-tuning\u002Freferences\u002Ftroubleshooting.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fmeta_schedule_import_probe.py","SCRIPT","脚本",1334,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftvm\u002Fsub-skills\u002Fs-tir-tuning\u002Fscripts\u002Fmeta_schedule_import_probe.py",[68,75,82,89,96,103],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"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.","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":14,"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":14,"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":14,"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":14,"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":14,"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",[],[]]