[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M791VBJSZW0775HMXMNR2PWT":3,"skill-same:01M791VBJSZW0775HMXMNR2PWT":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},"01M791VBJSZW0775HMXMNR2PWT","model-backends",null,"Configure OpenCompass model backends including HuggingFace, API, custom wrappers, LMDeploy, vLLM, credentials, resource run_cfg, tokenizer\u002Fmodel kwargs, batching, and backend 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\u002Fopencompass\u002Fsub-skills\u002Fmodel-backends\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: model-backends\ndescription: \"Configure OpenCompass model backends including HuggingFace, API,\n  custom wrappers, LMDeploy, vLLM, credentials, resource run_cfg,\n  tokenizer\u002Fmodel kwargs, batching, and backend troubleshooting.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Model Backends\n\nUse this sub-skill when an OpenCompass task is about model configuration rather than dataset selection, prompt construction, or workflow launch. It covers HuggingFace\u002Flocal models, API providers, accelerated LMDeploy\u002FvLLM\u002FLightLLM-style backends, custom model wrappers, credentials, and resource sizing.\n\n## Route by Backend\n\n- HuggingFace\u002Flocal Transformers models: use `references\u002Fmodel-configuration.md` for `HuggingFace`, `HuggingFaceCausalLM`, `HuggingFacewithChatTemplate`, tokenizer\u002Fmodel kwargs, `batch_size`, `max_seq_len`, `max_out_len`, `batch_padding`, and `run_cfg`.\n- API models: use `references\u002Fapi-models.md` for `OpenAI`, `OpenAISDK`, `TurboMindAPIModel`, credential handling, `query_per_second`, `retry`, `rpm_verbose`, `openai_api_base`, and no-network config checks.\n- Accelerated local backends: use `references\u002Fbackend-compatibility.md` for `--accelerator {vllm,lmdeploy,None}`, direct `VLLM` configs, direct `TurboMindModel` configs, service-based acceleration, and optional dependency boundaries.\n- New\u002Fcustom model support: use `references\u002Fmodel-configuration.md#custom-model-extension-route` when an existing OpenCompass backend cannot express the target model.\n- Backend failures: use `references\u002Ftroubleshooting.md` before changing datasets, prompts, summarizers, or evaluation mode.\n\n## Boundaries\n\n- For prompt templates, `meta_template`, and generation prompt behavior, coordinate with `..\u002Fprompt-and-inference\u002FSKILL.md` if present.\n- For dataset imports, config composition, and `read_base()` patterns, coordinate with `..\u002Fconfiguration-and-datasets\u002FSKILL.md` if present.\n- For `opencompass` CLI launch modes, `--mode`, `--reuse`, runners, and work directories, coordinate with `..\u002Fevaluation-workflows\u002FSKILL.md` if present.\n- Do not claim real HuggingFace\u002FGPU\u002FAPI inference is verified unless a task explicitly runs it in a suitable environment with required optional extras and credentials.\n\n## Bundled Script\n\n- `scripts\u002Fcheck_api_model_config.py`: loads an OpenCompass config, inspects model dictionaries, identifies likely API models, checks credential placeholders\u002Fenvironment-variable references, validates common API rate\u002Fresource fields, and exits before building models or making network calls.\n","# Model Backends\n\nUse this sub-skill when an OpenCompass task is about model configuration rather than dataset selection, prompt construction, or workflow launch. It covers HuggingFace\u002Flocal models, API providers, accelerated LMDeploy\u002FvLLM\u002FLightLLM-style backends, custom model wrappers, credentials, and resource sizing.\n\n## Route by Backend\n\n- HuggingFace\u002Flocal Transformers models: use `references\u002Fmodel-configuration.md` for `HuggingFace`, `HuggingFaceCausalLM`, `HuggingFacewithChatTemplate`, tokenizer\u002Fmodel kwargs, `batch_size`, `max_seq_len`, `max_out_len`, `batch_padding`, and `run_cfg`.\n- API models: use `references\u002Fapi-models.md` for `OpenAI`, `OpenAISDK`, `TurboMindAPIModel`, credential handling, `query_per_second`, `retry`, `rpm_verbose`, `openai_api_base`, and no-network config checks.\n- Accelerated local backends: use `references\u002Fbackend-compatibility.md` for `--accelerator {vllm,lmdeploy,None}`, direct `VLLM` configs, direct `TurboMindModel` configs, service-based acceleration, and optional dependency boundaries.\n- New\u002Fcustom model support: use `references\u002Fmodel-configuration.md#custom-model-extension-route` when an existing OpenCompass backend cannot express the target model.\n- Backend failures: use `references\u002Ftroubleshooting.md` before changing datasets, prompts, summarizers, or evaluation mode.\n\n## Boundaries\n\n- For prompt templates, `meta_template`, and generation prompt behavior, coordinate with `..\u002Fprompt-and-inference\u002FSKILL.md` if present.\n- For dataset imports, config composition, and `read_base()` patterns, coordinate with `..\u002Fconfiguration-and-datasets\u002FSKILL.md` if present.\n- For `opencompass` CLI launch modes, `--mode`, `--reuse`, runners, and work directories, coordinate with `..\u002Fevaluation-workflows\u002FSKILL.md` if present.\n- Do not claim real HuggingFace\u002FGPU\u002FAPI inference is verified unless a task explicitly runs it in a suitable environment with required optional extras and credentials.\n\n## Bundled Script\n\n- `scripts\u002Fcheck_api_model_config.py`: loads an OpenCompass config, inspects model dictionaries, identifies likely API models, checks credential placeholders\u002Fenvironment-variable references, validates common API rate\u002Fresource fields, and exits before building models or making network calls.\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\u002Fopencompass\u002Fsub-skills\u002Fmodel-backends",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-backends",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill model-backends",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill model-backends","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fopencompass\u002Fsub-skills\u002Fmodel-backends\u002FSKILL.md",[47,53,57,61,65],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fapi-models.md","REFERENCE","参考文档",5857,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fopencompass\u002Fsub-skills\u002Fmodel-backends\u002Freferences\u002Fapi-models.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fbackend-compatibility.md",6638,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fopencompass\u002Fsub-skills\u002Fmodel-backends\u002Freferences\u002Fbackend-compatibility.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fmodel-configuration.md",6612,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fopencompass\u002Fsub-skills\u002Fmodel-backends\u002Freferences\u002Fmodel-configuration.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Ftroubleshooting.md",5938,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fopencompass\u002Fsub-skills\u002Fmodel-backends\u002Freferences\u002Ftroubleshooting.md",{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Fcheck_api_model_config.py","SCRIPT","脚本",9076,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fopencompass\u002Fsub-skills\u002Fmodel-backends\u002Fscripts\u002Fcheck_api_model_config.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",[],[]]