[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M797PYD7HDFQRA41S74MENAM":3,"skill-same:01M797PYD7HDFQRA41S74MENAM":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},"01M797PYD7HDFQRA41S74MENAM","deployment",null,"Guides Zero123Plus demo, serving, and Cog deployment workflows, including Gradio, Streamlit, checkpoints, UI options, and deployment failures.","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\u002Fzero123plus\u002Fsub-skills\u002Fdeployment\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: deployment\ndescription: \"Guides Zero123Plus demo, serving, and Cog deployment workflows,\n  including Gradio, Streamlit, checkpoints, UI options, and deployment\n  failures.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Zero123Plus Deployment\n\nUse this sub-skill when a task is about launching, adapting, packaging, or\ntroubleshooting Zero123Plus demos and service surfaces: Streamlit, Gradio,\nDocker\u002FGitpod-style environments, Cog\u002FReplicate predictors, checkpoint caches,\nports, sharing, queues, and UI options.\n\nDo **not** use this sub-skill as the main source for image-to-multiview\nalgorithm details, ControlNets, camera poses, or batch generation code. Route\nthose questions to the sibling generation sub-skill at\n[`..\u002Fgeneration\u002FSKILL.md`](..\u002Fgeneration\u002FSKILL.md), then return here for serving\nand deployment decisions.\n\n## Read first\n\n- [`references\u002Fdeployment.md`](references\u002Fdeployment.md): deployment surfaces,\n  dependency\u002Fbootstrap patterns, Docker\u002FGitpod\u002FCog behavior, and how the surfaces\n  differ.\n- [`references\u002Fdemo-options.md`](references\u002Fdemo-options.md): Streamlit and\n  Gradio UI inputs, preprocessing options, examples, and output behavior.\n- [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md): deployment\n  failure modes for checkpoints, rembg\u002FSAM, ports, queues, Cog weights, pget,\n  CUDA, and source demo side effects.\n\n## Bundled deployment templates\n\n- [`scripts\u002Flaunch_gradio_demo.py`](scripts\u002Flaunch_gradio_demo.py): a compact,\n  self-contained Gradio launcher template. It avoids model downloads by default;\n  pass `--allow-download` only when network\u002Fmodel fetching is approved.\n- [`scripts\u002Fcog_predictor.py`](scripts\u002Fcog_predictor.py): a self-contained Cog\n  predictor template with configurable cache\u002Fmodel paths and no model loading on\n  import.\n\n## Routing procedure\n\n1. Identify the requested surface: local Streamlit demo, Gradio demo, container\n   image, Gitpod-style workspace, Cog\u002FReplicate predictor, or a custom service.\n2. Check whether the user has approved network downloads and whether the runtime\n   has a CUDA GPU. Stop or ask before triggering Hugging Face model downloads,\n   SAM checkpoint downloads, rembg\u002FONNX model downloads, or Cog weight archive\n   fetches.\n3. For a safer local Gradio launch, prefer the bundled launcher template over\n   importing source UI modules. For Cog, adapt the bundled predictor template and\n   configure its environment variables instead of relying on checkout-relative\n   paths.\n4. For UI behavior, input preprocessing, background removal, and output layout,\n   read `references\u002Fdemo-options.md`. For exact pipeline arguments and generated\n   view semantics, route to `..\u002Fgeneration\u002FSKILL.md`.\n5. If a failure involves missing CUDA, unavailable weights, missing SAM\u002Frembg\n   components, blocked Gradio share tunnels, or Cog cache\u002Fdownload issues, use\n   `references\u002Ftroubleshooting.md` before proposing code changes.\n\n## Stop conditions\n\n- No CUDA GPU is available for an actual generation-backed demo or Cog run.\n- The required model\u002Fcheckpoint\u002Fcache is absent and downloads are not approved.\n- Background removal is required but `rembg`, `segment_anything`, or the SAM\n  checkpoint is missing and the user has not approved installing\u002Fdownloading it.\n- The request is really about generation APIs, ControlNet variants, or camera\n  outputs; route to the generation sub-skill instead of duplicating that logic\n  here.\n","# Zero123Plus Deployment\n\nUse this sub-skill when a task is about launching, adapting, packaging, or\ntroubleshooting Zero123Plus demos and service surfaces: Streamlit, Gradio,\nDocker\u002FGitpod-style environments, Cog\u002FReplicate predictors, checkpoint caches,\nports, sharing, queues, and UI options.\n\nDo **not** use this sub-skill as the main source for image-to-multiview\nalgorithm details, ControlNets, camera poses, or batch generation code. Route\nthose questions to the sibling generation sub-skill at\n[`..\u002Fgeneration\u002FSKILL.md`](..\u002Fgeneration\u002FSKILL.md), then return here for serving\nand deployment decisions.\n\n## Read first\n\n- [`references\u002Fdeployment.md`](references\u002Fdeployment.md): deployment surfaces,\n  dependency\u002Fbootstrap patterns, Docker\u002FGitpod\u002FCog behavior, and how the surfaces\n  differ.\n- [`references\u002Fdemo-options.md`](references\u002Fdemo-options.md): Streamlit and\n  Gradio UI inputs, preprocessing options, examples, and output behavior.\n- [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md): deployment\n  failure modes for checkpoints, rembg\u002FSAM, ports, queues, Cog weights, pget,\n  CUDA, and source demo side effects.\n\n## Bundled deployment templates\n\n- [`scripts\u002Flaunch_gradio_demo.py`](scripts\u002Flaunch_gradio_demo.py): a compact,\n  self-contained Gradio launcher template. It avoids model downloads by default;\n  pass `--allow-download` only when network\u002Fmodel fetching is approved.\n- [`scripts\u002Fcog_predictor.py`](scripts\u002Fcog_predictor.py): a self-contained Cog\n  predictor template with configurable cache\u002Fmodel paths and no model loading on\n  import.\n\n## Routing procedure\n\n1. Identify the requested surface: local Streamlit demo, Gradio demo, container\n   image, Gitpod-style workspace, Cog\u002FReplicate predictor, or a custom service.\n2. Check whether the user has approved network downloads and whether the runtime\n   has a CUDA GPU. Stop or ask before triggering Hugging Face model downloads,\n   SAM checkpoint downloads, rembg\u002FONNX model downloads, or Cog weight archive\n   fetches.\n3. For a safer local Gradio launch, prefer the bundled launcher template over\n   importing source UI modules. For Cog, adapt the bundled predictor template and\n   configure its environment variables instead of relying on checkout-relative\n   paths.\n4. For UI behavior, input preprocessing, background removal, and output layout,\n   read `references\u002Fdemo-options.md`. For exact pipeline arguments and generated\n   view semantics, route to `..\u002Fgeneration\u002FSKILL.md`.\n5. If a failure involves missing CUDA, unavailable weights, missing SAM\u002Frembg\n   components, blocked Gradio share tunnels, or Cog cache\u002Fdownload issues, use\n   `references\u002Ftroubleshooting.md` before proposing code changes.\n\n## Stop conditions\n\n- No CUDA GPU is available for an actual generation-backed demo or Cog run.\n- The required model\u002Fcheckpoint\u002Fcache is absent and downloads are not approved.\n- Background removal is required but `rembg`, `segment_anything`, or the SAM\n  checkpoint is missing and the user has not approved installing\u002Fdownloading it.\n- The request is really about generation APIs, ControlNet variants, or camera\n  outputs; route to the generation sub-skill instead of duplicating that logic\n  here.\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\u002Fzero123plus\u002Fsub-skills\u002Fdeployment",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 deployment",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill deployment",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill deployment","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fzero123plus\u002Fsub-skills\u002Fdeployment\u002FSKILL.md",[47,53,57,61,67],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fdemo-options.md","REFERENCE","参考文档",6913,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fzero123plus\u002Fsub-skills\u002Fdeployment\u002Freferences\u002Fdemo-options.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fdeployment.md",8612,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fzero123plus\u002Fsub-skills\u002Fdeployment\u002Freferences\u002Fdeployment.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",7366,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fzero123plus\u002Fsub-skills\u002Fdeployment\u002Freferences\u002Ftroubleshooting.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fcog_predictor.py","SCRIPT","脚本",8971,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fzero123plus\u002Fsub-skills\u002Fdeployment\u002Fscripts\u002Fcog_predictor.py",{"path":68,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Flaunch_gradio_demo.py",8863,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fzero123plus\u002Fsub-skills\u002Fdeployment\u002Fscripts\u002Flaunch_gradio_demo.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",[],[]]