[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7977R5EB40XVWHEB954SPCT":3,"skill-same:01M7977R5EB40XVWHEB954SPCT":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},"01M7977R5EB40XVWHEB954SPCT","model-integration",null,"Extend vLLM-Omni with custom diffusion pipelines, model registrations, TTS adapter contracts, and focused maintainer tests without running broad model suites by default.","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\u002Fvllm-omni\u002Fsub-skills\u002Fmodel-integration\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: model-integration\ndescription: \"Extend vLLM-Omni with custom diffusion pipelines, model\n  registrations, TTS adapter contracts, and focused maintainer tests without\n  running broad model suites by default.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Model integration\n\nUse this sub-skill when the user is editing or extending vLLM-Omni itself: adding a model family, wiring a custom diffusion pipeline, updating a TTS adapter, or choosing focused maintainer tests before a larger GPU run.\n\n## Route here for\n\n- Creating a custom diffusion pipeline using `diffusion_load_format`, `custom_pipeline_args`, `WorkerWrapperBase`, or `CustomPipelineWorkerExtension`.\n- Adding or updating an omni AR, diffusion, TTS, action\u002Fworld-model, or model-extra integration.\n- Registering a `model_type`, pipeline topology, default deploy config, endpoint restrictions, or serving adapter.\n- Reviewing OpenAI TTS adapter shape and optional dependency behavior.\n- Choosing focused CPU parser\u002Fconfig\u002Funit tests before expensive GPU\u002Ffull-model examples.\n\n## Route elsewhere\n\n- Local Python inference with existing models: use the sibling offline-inference sub-skill.\n- HTTP serving payloads and server launch commands: use the sibling online-serving sub-skill.\n- Deploy YAML overlays, connectors, placement, or memory planning: use the sibling stage-configuration sub-skill.\n- Choosing an already supported model\u002Frecipe\u002Fbackend: use the sibling model-recipes sub-skill.\n\n## Start here\n\n1. Read [custom-pipeline-and-model-registration.md](references\u002Fcustom-pipeline-and-model-registration.md) for extension surfaces and registration flow.\n2. Read [maintainer-workflows.md](references\u002Fmaintainer-workflows.md) before selecting tests or editing broad model code.\n3. For TTS adapter edits, run or adapt the safe static checker:\n\n   ```bash\n   python scripts\u002Fcheck_tts_adapter_contract.py --adapter-file path\u002Fto\u002Fadapter.py\n   ```\n\n   The checker parses source; it does not import the adapter, load a model, or call audio services.\n4. Use [troubleshooting.md](references\u002Ftroubleshooting.md) when registrations are not discovered, a deploy YAML does not match a pipeline, optional dependencies are missing, or a model test is too expensive.\n\n## Safety rules\n\n- Do CPU\u002Fstatic checks before GPU e2e tests. Full-model examples usually require model checkpoints, CUDA\u002Faccelerator hardware, large VRAM, and time.\n- Keep custom-pipeline examples self-contained. Do not require future agents to open original examples before implementing a pipeline.\n- Treat vendored\u002Fupstream model code as parity-sensitive; avoid style rewrites that make future upstream diffs hard.\n- If a change touches endpoint contracts, update serving payload guidance in online-serving as well.\n- If a change touches deploy topology or defaults, update stage-configuration guidance as well.\n","# Model integration\n\nUse this sub-skill when the user is editing or extending vLLM-Omni itself: adding a model family, wiring a custom diffusion pipeline, updating a TTS adapter, or choosing focused maintainer tests before a larger GPU run.\n\n## Route here for\n\n- Creating a custom diffusion pipeline using `diffusion_load_format`, `custom_pipeline_args`, `WorkerWrapperBase`, or `CustomPipelineWorkerExtension`.\n- Adding or updating an omni AR, diffusion, TTS, action\u002Fworld-model, or model-extra integration.\n- Registering a `model_type`, pipeline topology, default deploy config, endpoint restrictions, or serving adapter.\n- Reviewing OpenAI TTS adapter shape and optional dependency behavior.\n- Choosing focused CPU parser\u002Fconfig\u002Funit tests before expensive GPU\u002Ffull-model examples.\n\n## Route elsewhere\n\n- Local Python inference with existing models: use the sibling offline-inference sub-skill.\n- HTTP serving payloads and server launch commands: use the sibling online-serving sub-skill.\n- Deploy YAML overlays, connectors, placement, or memory planning: use the sibling stage-configuration sub-skill.\n- Choosing an already supported model\u002Frecipe\u002Fbackend: use the sibling model-recipes sub-skill.\n\n## Start here\n\n1. Read [custom-pipeline-and-model-registration.md](references\u002Fcustom-pipeline-and-model-registration.md) for extension surfaces and registration flow.\n2. Read [maintainer-workflows.md](references\u002Fmaintainer-workflows.md) before selecting tests or editing broad model code.\n3. For TTS adapter edits, run or adapt the safe static checker:\n\n   ```bash\n   python scripts\u002Fcheck_tts_adapter_contract.py --adapter-file path\u002Fto\u002Fadapter.py\n   ```\n\n   The checker parses source; it does not import the adapter, load a model, or call audio services.\n4. Use [troubleshooting.md](references\u002Ftroubleshooting.md) when registrations are not discovered, a deploy YAML does not match a pipeline, optional dependencies are missing, or a model test is too expensive.\n\n## Safety rules\n\n- Do CPU\u002Fstatic checks before GPU e2e tests. Full-model examples usually require model checkpoints, CUDA\u002Faccelerator hardware, large VRAM, and time.\n- Keep custom-pipeline examples self-contained. Do not require future agents to open original examples before implementing a pipeline.\n- Treat vendored\u002Fupstream model code as parity-sensitive; avoid style rewrites that make future upstream diffs hard.\n- If a change touches endpoint contracts, update serving payload guidance in online-serving as well.\n- If a change touches deploy topology or defaults, update stage-configuration guidance as well.\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\u002Fvllm-omni\u002Fsub-skills\u002Fmodel-integration",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 model-integration",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill model-integration",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill model-integration","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fvllm-omni\u002Fsub-skills\u002Fmodel-integration\u002FSKILL.md",[47,53,57,61],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fcustom-pipeline-and-model-registration.md","REFERENCE","参考文档",6722,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fvllm-omni\u002Fsub-skills\u002Fmodel-integration\u002Freferences\u002Fcustom-pipeline-and-model-registration.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fmaintainer-workflows.md",4862,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fvllm-omni\u002Fsub-skills\u002Fmodel-integration\u002Freferences\u002Fmaintainer-workflows.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",4710,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fvllm-omni\u002Fsub-skills\u002Fmodel-integration\u002Freferences\u002Ftroubleshooting.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fcheck_tts_adapter_contract.py","SCRIPT","脚本",9045,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fvllm-omni\u002Fsub-skills\u002Fmodel-integration\u002Fscripts\u002Fcheck_tts_adapter_contract.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",[],[]]