[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M796SCTW55MMVBT5JDCKHDXP":3,"skill-same:01M796SCTW55MMVBT5JDCKHDXP":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},"01M796SCTW55MMVBT5JDCKHDXP","rpc-deployment",null,"Guides TVM RPC tracker\u002Fserver\u002Fproxy setup, cross-compilation, remote module upload\u002Fload\u002Frun, and deployment troubleshooting.","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\u002Frpc-deployment\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: rpc-deployment\ndescription: \"Guides TVM RPC tracker\u002Fserver\u002Fproxy setup, cross-compilation,\n  remote module upload\u002Fload\u002Frun, and deployment troubleshooting.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# TVM RPC and Deployment\n\nUse this route when a task involves TVM RPC, cross-compilation, remote device\nexecution, tracker\u002Fserver\u002Fproxy commands, module upload\u002Fload, target triples,\nremote timing, or RPC-backed meta-schedule runners.\n\n## Route\n\n1. Confirm local TVM import and target compile support. Use\n   [`..\u002Finstall-build\u002FSKILL.md`](..\u002Finstall-build\u002FSKILL.md) for build\u002Fimport\n   failures.\n2. Decide whether the task needs direct RPC server, tracker-managed devices, or\n   a proxy. Read [`references\u002Fcli-and-runtime.md`](references\u002Fcli-and-runtime.md).\n3. For cross-compilation and remote execution, read\n   [`references\u002Fcross-compilation.md`](references\u002Fcross-compilation.md) and keep\n   target triple, device runtime, export artifact, upload path, and run device\n   explicit.\n4. Run [`scripts\u002Frpc_cli_help_probe.py`](scripts\u002Frpc_cli_help_probe.py) for safe\n   CLI\u002FAPI availability. It prints help text and does not start persistent\n   services.\n5. Use [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) for port\n   conflicts, keys, timeouts, tracker query failures, target-host mismatch,\n   module load errors, and remote device availability.\n\n## API anchors\n\n```python\nfrom tvm import rpc\n\nremote = rpc.connect(url, port, key=\"\", session_timeout=0)\ntracker = rpc.connect_tracker(url, port)\nremote.upload(\"lib.tar\")\nfunc = remote.load_module(\"lib.tar\")\ndev = remote.cpu(0)\n```\n\nUse `rpc.LocalSession()` for a local smoke that exercises upload\u002Fload\u002Frun\nwithout opening a network listener.\n\n## CLI anchors\n\n```bash\npython -m tvm.exec.rpc_server --host 0.0.0.0 --port 9090\npython -m tvm.exec.rpc_tracker --host 0.0.0.0 --port 9190 --port-end 9191\npython -m tvm.exec.query_rpc_tracker --host TRACKER_HOST --port 9190\npython -m tvm.exec.rpc_proxy --host PROXY_HOST --port 9090 --tracker TRACKER_HOST:9190\n```\n\nStart long-lived services only after the user approves host\u002Fport\u002Fkey choices and\nknows how to stop the processes.\n\n## Boundaries\n\n- Relax compilation before export: [`..\u002Frelax-compile\u002FSKILL.md`](..\u002Frelax-compile\u002FSKILL.md).\n- S-TIR\u002Fmeta-schedule runner selection: [`..\u002Fs-tir-tuning\u002FSKILL.md`](..\u002Fs-tir-tuning\u002FSKILL.md).\n- TIRx CUDA kernel codegen: [`..\u002Ftirx-kernels\u002FSKILL.md`](..\u002Ftirx-kernels\u002FSKILL.md).\n","# TVM RPC and Deployment\n\nUse this route when a task involves TVM RPC, cross-compilation, remote device\nexecution, tracker\u002Fserver\u002Fproxy commands, module upload\u002Fload, target triples,\nremote timing, or RPC-backed meta-schedule runners.\n\n## Route\n\n1. Confirm local TVM import and target compile support. Use\n   [`..\u002Finstall-build\u002FSKILL.md`](..\u002Finstall-build\u002FSKILL.md) for build\u002Fimport\n   failures.\n2. Decide whether the task needs direct RPC server, tracker-managed devices, or\n   a proxy. Read [`references\u002Fcli-and-runtime.md`](references\u002Fcli-and-runtime.md).\n3. For cross-compilation and remote execution, read\n   [`references\u002Fcross-compilation.md`](references\u002Fcross-compilation.md) and keep\n   target triple, device runtime, export artifact, upload path, and run device\n   explicit.\n4. Run [`scripts\u002Frpc_cli_help_probe.py`](scripts\u002Frpc_cli_help_probe.py) for safe\n   CLI\u002FAPI availability. It prints help text and does not start persistent\n   services.\n5. Use [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) for port\n   conflicts, keys, timeouts, tracker query failures, target-host mismatch,\n   module load errors, and remote device availability.\n\n## API anchors\n\n```python\nfrom tvm import rpc\n\nremote = rpc.connect(url, port, key=\"\", session_timeout=0)\ntracker = rpc.connect_tracker(url, port)\nremote.upload(\"lib.tar\")\nfunc = remote.load_module(\"lib.tar\")\ndev = remote.cpu(0)\n```\n\nUse `rpc.LocalSession()` for a local smoke that exercises upload\u002Fload\u002Frun\nwithout opening a network listener.\n\n## CLI anchors\n\n```bash\npython -m tvm.exec.rpc_server --host 0.0.0.0 --port 9090\npython -m tvm.exec.rpc_tracker --host 0.0.0.0 --port 9190 --port-end 9191\npython -m tvm.exec.query_rpc_tracker --host TRACKER_HOST --port 9190\npython -m tvm.exec.rpc_proxy --host PROXY_HOST --port 9090 --tracker TRACKER_HOST:9190\n```\n\nStart long-lived services only after the user approves host\u002Fport\u002Fkey choices and\nknows how to stop the processes.\n\n## Boundaries\n\n- Relax compilation before export: [`..\u002Frelax-compile\u002FSKILL.md`](..\u002Frelax-compile\u002FSKILL.md).\n- S-TIR\u002Fmeta-schedule runner selection: [`..\u002Fs-tir-tuning\u002FSKILL.md`](..\u002Fs-tir-tuning\u002FSKILL.md).\n- TIRx CUDA kernel codegen: [`..\u002Ftirx-kernels\u002FSKILL.md`](..\u002Ftirx-kernels\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\u002Frpc-deployment",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 rpc-deployment",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill rpc-deployment",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill rpc-deployment","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftvm\u002Fsub-skills\u002Frpc-deployment\u002FSKILL.md",[47,53,57,61],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fcli-and-runtime.md","REFERENCE","参考文档",2106,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftvm\u002Fsub-skills\u002Frpc-deployment\u002Freferences\u002Fcli-and-runtime.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fcross-compilation.md",2476,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftvm\u002Fsub-skills\u002Frpc-deployment\u002Freferences\u002Fcross-compilation.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",1989,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftvm\u002Fsub-skills\u002Frpc-deployment\u002Freferences\u002Ftroubleshooting.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Frpc_cli_help_probe.py","SCRIPT","脚本",2085,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftvm\u002Fsub-skills\u002Frpc-deployment\u002Fscripts\u002Frpc_cli_help_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",[],[]]