[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M796SAZD0TJANDBVW6K6VF0H":3,"skill-same:01M796SAZD0TJANDBVW6K6VF0H":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},"01M796SAZD0TJANDBVW6K6VF0H","relax-compile",null,"Guides TVM Relax IR construction\u002Fimport, optimization pipelines, tvm.compile, executable export\u002Fload, and custom codegen boundaries.","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\u002Frelax-compile\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: relax-compile\ndescription: \"Guides TVM Relax IR construction\u002Fimport, optimization pipelines,\n  tvm.compile, executable export\u002Fload, and custom codegen boundaries.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Relax Compile Workflows\n\nUse this sub-skill when a task involves high-level TVM Relax IR, model import,\noptimization pipelines, `tvm.compile`, VM execution, or deployable executable\nartifacts.\n\n## Route\n\n1. Confirm TVM imports and has the target backend required by the task. If not,\n   first use [`..\u002Finstall-build\u002FSKILL.md`](..\u002Finstall-build\u002FSKILL.md).\n2. Decide how the IRModule is created: Relax NN frontend, TVMScript Relax,\n   PyTorch\u002FONNX frontend import, or an existing IRModule.\n3. Apply the smallest needed pipeline or pass sequence. `relax.get_pipeline(\"zero\")`\n   is a safe baseline for tutorial-style CPU workflows; larger model and dlight\n   flows need backend-specific checks.\n4. Compile through `tvm.compile(mod, target, relax_pipeline=..., tir_pipeline=...)`.\n5. Run the executable locally with `relax.VirtualMachine` or export\u002Fload it for a\n   deployment workflow.\n6. Use [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) when the\n   failure is about target mismatch, optional frontend dependencies, export\u002Fload,\n   or pass\u002Fcodegen boundaries.\n\n## Common decisions\n\n- **Tiny local CPU compile:** create or adapt a small Relax IRModule and target\n  `llvm`. Run [`scripts\u002Frelax_compile_smoke.py`](scripts\u002Frelax_compile_smoke.py)\n  before diagnosing a larger model.\n- **PyTorch or ONNX import:** require the matching frontend dependency and a\n  small example input. Keep model downloads, weights, and external datasets out\n  of the first debugging loop.\n- **Custom optimization:** keep Relax graph passes and TIR\u002FS-TIR scheduling\n  passes separate. Route schedule\u002Fmeta-schedule decisions to\n  [`..\u002Fs-tir-tuning\u002FSKILL.md`](..\u002Fs-tir-tuning\u002FSKILL.md).\n- **Remote execution:** compile\u002Fexport locally, then use\n  [`..\u002Frpc-deployment\u002FSKILL.md`](..\u002Frpc-deployment\u002FSKILL.md) for upload\u002Fload\u002Frun\n  and tracker\u002Fserver details.\n\n## API anchor\n\nThe verified top-level compile entry point is:\n\n```python\ntvm.compile(\n    mod,\n    target=None,\n    *,\n    relax_pipeline=\"default\",\n    tir_pipeline=\"default\",\n)\n```\n\nIt accepts a Relax\u002FTIR IRModule or TIRx PrimFunc and returns a runtime\n`Executable`. The pipeline arguments accept a named pipeline, pass object, or\ncallable depending on the workflow.\n\n## Boundaries\n\n- Build\u002Fimport failures are not Relax failures; route to install-build.\n- TIRx PrimFunc authoring and tile primitive lowering use tirx-kernels.\n- S-TIR schedule primitives and meta-schedule tuning use s-tir-tuning.\n- RPC trackers, servers, proxies, and remote-device triage use rpc-deployment.\n","# Relax Compile Workflows\n\nUse this sub-skill when a task involves high-level TVM Relax IR, model import,\noptimization pipelines, `tvm.compile`, VM execution, or deployable executable\nartifacts.\n\n## Route\n\n1. Confirm TVM imports and has the target backend required by the task. If not,\n   first use [`..\u002Finstall-build\u002FSKILL.md`](..\u002Finstall-build\u002FSKILL.md).\n2. Decide how the IRModule is created: Relax NN frontend, TVMScript Relax,\n   PyTorch\u002FONNX frontend import, or an existing IRModule.\n3. Apply the smallest needed pipeline or pass sequence. `relax.get_pipeline(\"zero\")`\n   is a safe baseline for tutorial-style CPU workflows; larger model and dlight\n   flows need backend-specific checks.\n4. Compile through `tvm.compile(mod, target, relax_pipeline=..., tir_pipeline=...)`.\n5. Run the executable locally with `relax.VirtualMachine` or export\u002Fload it for a\n   deployment workflow.\n6. Use [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) when the\n   failure is about target mismatch, optional frontend dependencies, export\u002Fload,\n   or pass\u002Fcodegen boundaries.\n\n## Common decisions\n\n- **Tiny local CPU compile:** create or adapt a small Relax IRModule and target\n  `llvm`. Run [`scripts\u002Frelax_compile_smoke.py`](scripts\u002Frelax_compile_smoke.py)\n  before diagnosing a larger model.\n- **PyTorch or ONNX import:** require the matching frontend dependency and a\n  small example input. Keep model downloads, weights, and external datasets out\n  of the first debugging loop.\n- **Custom optimization:** keep Relax graph passes and TIR\u002FS-TIR scheduling\n  passes separate. Route schedule\u002Fmeta-schedule decisions to\n  [`..\u002Fs-tir-tuning\u002FSKILL.md`](..\u002Fs-tir-tuning\u002FSKILL.md).\n- **Remote execution:** compile\u002Fexport locally, then use\n  [`..\u002Frpc-deployment\u002FSKILL.md`](..\u002Frpc-deployment\u002FSKILL.md) for upload\u002Fload\u002Frun\n  and tracker\u002Fserver details.\n\n## API anchor\n\nThe verified top-level compile entry point is:\n\n```python\ntvm.compile(\n    mod,\n    target=None,\n    *,\n    relax_pipeline=\"default\",\n    tir_pipeline=\"default\",\n)\n```\n\nIt accepts a Relax\u002FTIR IRModule or TIRx PrimFunc and returns a runtime\n`Executable`. The pipeline arguments accept a named pipeline, pass object, or\ncallable depending on the workflow.\n\n## Boundaries\n\n- Build\u002Fimport failures are not Relax failures; route to install-build.\n- TIRx PrimFunc authoring and tile primitive lowering use tirx-kernels.\n- S-TIR schedule primitives and meta-schedule tuning use s-tir-tuning.\n- RPC trackers, servers, proxies, and remote-device triage use rpc-deployment.\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\u002Frelax-compile",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 relax-compile",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill relax-compile",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill relax-compile","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftvm\u002Fsub-skills\u002Frelax-compile\u002FSKILL.md",[47,53,57,61],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fapi-reference.md","REFERENCE","参考文档",2430,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftvm\u002Fsub-skills\u002Frelax-compile\u002Freferences\u002Fapi-reference.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Ftroubleshooting.md",2165,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftvm\u002Fsub-skills\u002Frelax-compile\u002Freferences\u002Ftroubleshooting.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fworkflows.md",3506,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftvm\u002Fsub-skills\u002Frelax-compile\u002Freferences\u002Fworkflows.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Frelax_compile_smoke.py","SCRIPT","脚本",2689,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftvm\u002Fsub-skills\u002Frelax-compile\u002Fscripts\u002Frelax_compile_smoke.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",[],[]]