[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78SFAM337HP35ZCW7JFVHG3":3,"skill-same:01M78SFAM337HP35ZCW7JFVHG3":71},{"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},"01M78SFAM337HP35ZCW7JFVHG3","inference",null,"End-to-end Alpamayo R1 multimodal driving inference, sample generation, and 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\u002Falpamayo-r1\u002Fsub-skills\u002Finference\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: inference\ndescription: \"End-to-end Alpamayo R1 multimodal driving inference, sample\n  generation, and troubleshooting.\"\nmetadata:\n  disco-role: operating\ndisable-model-invocation: true\nlicense: Apache 2.0\n---\n\n# Alpamayo R1 Inference\n\nUse this sub-skill when the user wants to run, inspect, or adapt the Alpamayo R1 inference path on a PhysicalAI-AV clip.\n\n## What this covers\n\n- Load a gated PhysicalAI-AV clip and egomotion history\u002Ffuture.\n- Build the multimodal chat prompt from stacked camera frames.\n- Load `nvidia\u002FAlpamayo-R1-10B` on CUDA with the Alpamayo tokenizer and processor.\n- Sample future trajectories plus Chain-of-Causation text traces.\n- Compare predicted trajectories with ground truth and visualize them in notebook style.\n- Troubleshoot HF gating, CUDA OOM, flash-attn \u002F SDPA fallback, device placement, prompt rank, and early `t0_us` failures.\n\n## What this does not cover\n\n- Training, SFT, RL post-training, or repo maintenance.\n- Import\u002Fexport plumbing or package provenance.\n- Any workflow that depends on the original checkout at runtime.\n\n## Fast route\n\n1. Read `references\u002Fapi-reference.md` for the public call contract.\n2. Read `references\u002Fdata-formats.md` for shapes, frames, and output semantics.\n3. Follow `references\u002Fworkflows.md` for the end-to-end inference flow and notebook-style visualization.\n4. If anything fails, open `references\u002Ftroubleshooting.md`.\n5. Run `scripts\u002Frun_inference_smoke.py` as the bundled smoke test.\n\n## Key defaults\n\n- Default model id: `nvidia\u002FAlpamayo-R1-10B`\n- Default loader history \u002F future \u002F camera settings: 16 steps, 64 steps, 4 cameras\n- Default attention path: `flash_attention_2`\n- SDPA is a fallback for flash-attn incompatibility, not a replacement for the CUDA path.\n\n## See also\n\n- `..\u002F..\u002FSKILL.md` for the root router\n- `..\u002F..\u002Freferences\u002Frepo-provenance.md`\n- `..\u002F..\u002Freferences\u002Frepo-routing-metadata.json`\n- `..\u002F..\u002Freferences\u002Ftroubleshooting.md` for shared Alpamayo R1 troubleshooting\n- `references\u002Fapi-reference.md`\n- `references\u002Fdata-formats.md`\n- `references\u002Fworkflows.md`\n- `references\u002Ftroubleshooting.md`\n- `scripts\u002Frun_inference_smoke.py`\n","# Alpamayo R1 Inference\n\nUse this sub-skill when the user wants to run, inspect, or adapt the Alpamayo R1 inference path on a PhysicalAI-AV clip.\n\n## What this covers\n\n- Load a gated PhysicalAI-AV clip and egomotion history\u002Ffuture.\n- Build the multimodal chat prompt from stacked camera frames.\n- Load `nvidia\u002FAlpamayo-R1-10B` on CUDA with the Alpamayo tokenizer and processor.\n- Sample future trajectories plus Chain-of-Causation text traces.\n- Compare predicted trajectories with ground truth and visualize them in notebook style.\n- Troubleshoot HF gating, CUDA OOM, flash-attn \u002F SDPA fallback, device placement, prompt rank, and early `t0_us` failures.\n\n## What this does not cover\n\n- Training, SFT, RL post-training, or repo maintenance.\n- Import\u002Fexport plumbing or package provenance.\n- Any workflow that depends on the original checkout at runtime.\n\n## Fast route\n\n1. Read `references\u002Fapi-reference.md` for the public call contract.\n2. Read `references\u002Fdata-formats.md` for shapes, frames, and output semantics.\n3. Follow `references\u002Fworkflows.md` for the end-to-end inference flow and notebook-style visualization.\n4. If anything fails, open `references\u002Ftroubleshooting.md`.\n5. Run `scripts\u002Frun_inference_smoke.py` as the bundled smoke test.\n\n## Key defaults\n\n- Default model id: `nvidia\u002FAlpamayo-R1-10B`\n- Default loader history \u002F future \u002F camera settings: 16 steps, 64 steps, 4 cameras\n- Default attention path: `flash_attention_2`\n- SDPA is a fallback for flash-attn incompatibility, not a replacement for the CUDA path.\n\n## See also\n\n- `..\u002F..\u002FSKILL.md` for the root router\n- `..\u002F..\u002Freferences\u002Frepo-provenance.md`\n- `..\u002F..\u002Freferences\u002Frepo-routing-metadata.json`\n- `..\u002F..\u002Freferences\u002Ftroubleshooting.md` for shared Alpamayo R1 troubleshooting\n- `references\u002Fapi-reference.md`\n- `references\u002Fdata-formats.md`\n- `references\u002Fworkflows.md`\n- `references\u002Ftroubleshooting.md`\n- `scripts\u002Frun_inference_smoke.py`\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\u002Falpamayo-r1\u002Fsub-skills\u002Finference",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 inference",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill inference",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill inference","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Falpamayo-r1\u002Fsub-skills\u002Finference\u002FSKILL.md",[47,53,57,61,65],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fapi-reference.md","REFERENCE","参考文档",4098,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Falpamayo-r1\u002Fsub-skills\u002Finference\u002Freferences\u002Fapi-reference.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fdata-formats.md",3640,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Falpamayo-r1\u002Fsub-skills\u002Finference\u002Freferences\u002Fdata-formats.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",4815,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Falpamayo-r1\u002Fsub-skills\u002Finference\u002Freferences\u002Ftroubleshooting.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Fworkflows.md",4410,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Falpamayo-r1\u002Fsub-skills\u002Finference\u002Freferences\u002Fworkflows.md",{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Frun_inference_smoke.py","SCRIPT","脚本",7855,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Falpamayo-r1\u002Fsub-skills\u002Finference\u002Fscripts\u002Frun_inference_smoke.py",[72,79,86,93,100,107],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"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":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"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":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"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":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"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":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"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":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"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",[],[]]