[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M790X9CC482M66WJ84PP2C6F":3,"skill-same:01M790X9CC482M66WJ84PP2C6F":75},{"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},"01M790X9CC482M66WJ84PP2C6F","inference-deployment",null,"Run and debug ms-swift inference, app, deployment, backend selection, OpenAI-compatible serving, multimodal requests, adapters, and result\u002Flogprob workflows.","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\u002Fms-swift\u002Fsub-skills\u002Finference-deployment\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: inference-deployment\ndescription: \"Run and debug ms-swift inference, app, deployment, backend\n  selection, OpenAI-compatible serving, multimodal requests, adapters, and\n  result\u002Flogprob workflows.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Inference and Deployment\n\nUse this sub-skill when an agent needs to run `swift infer`, `swift app`, or `swift deploy`, choose an inference backend, call a local OpenAI-compatible server, use `swift.infer_engine` Python APIs, or debug serving\u002Fruntime failures.\n\n## Route first\n\n- Use `references\u002Fworkflows.md` for concrete CLI, app, deploy, client, batch, multimodal, LoRA, logprob, and result-saving recipes.\n- Use `references\u002Fapi-reference.md` for `InferArguments`, `DeployArguments`, `AppArguments`, `InferRequest`, `RequestConfig`, engines, OpenAI endpoints, and Python client shapes.\n- Use `references\u002Fbackend-compatibility.md` before selecting `transformers`, `vllm`, `sglang`, or `lmdeploy`.\n- Use `references\u002Ftroubleshooting.md` for backend\u002Fmodel mismatches, optional dependency failures, QLoRA limitations, multimodal OOM, `vllm_limit_mm_per_prompt`, result\u002Flogprob surprises, adapter loading, and unreachable local servers.\n- Use `scripts\u002Fbuild_inference_command.py` to print safe `swift infer`, `swift deploy`, or `swift app` command skeletons without launching models.\n- Use `scripts\u002Fsmoke_openai_client.py` to test a local OpenAI-compatible `\u002Fv1\u002Fchat\u002Fcompletions` server; it targets localhost by default and does not use external network resources.\n\n## Use cases covered here\n\n- Interactive text or multimodal CLI inference with `swift infer`.\n- Dataset or batch inference with saved JSONL results and optional metrics\u002Flogprobs.\n- Local Gradio-style inference UI with `swift app`, either self-hosting a model or connecting to an existing base URL.\n- OpenAI-compatible serving with `swift deploy`, including `\u002Fv1\u002Fmodels`, `\u002Fv1\u002Fchat\u002Fcompletions`, `\u002Fv1\u002Fcompletions`, `\u002Fv1\u002Fembeddings`, health\u002Fping, and Swift client calls.\n- Backend selection across `transformers`, `vllm`, `sglang`, and `lmdeploy`, including optional dependency caveats.\n- Full checkpoint, LoRA adapter, merged LoRA, and multiple named LoRA serving plans.\n\n## Reroute boundaries\n\n- Training command construction, checkpoint creation, and LoRA training arguments belong to the training sub-skill.\n- Dataset schema design and custom dataset registration belong to data\u002Fmodel customization.\n- Export, merge-only packaging, quantization, and evaluation pipelines belong to export\u002Fevaluation.\n- GRPO rollout, Ray, and Megatron serving\u002Fsampling internals belong to advanced RL\u002Fdistributed workflows.\n","# Inference and Deployment\n\nUse this sub-skill when an agent needs to run `swift infer`, `swift app`, or `swift deploy`, choose an inference backend, call a local OpenAI-compatible server, use `swift.infer_engine` Python APIs, or debug serving\u002Fruntime failures.\n\n## Route first\n\n- Use `references\u002Fworkflows.md` for concrete CLI, app, deploy, client, batch, multimodal, LoRA, logprob, and result-saving recipes.\n- Use `references\u002Fapi-reference.md` for `InferArguments`, `DeployArguments`, `AppArguments`, `InferRequest`, `RequestConfig`, engines, OpenAI endpoints, and Python client shapes.\n- Use `references\u002Fbackend-compatibility.md` before selecting `transformers`, `vllm`, `sglang`, or `lmdeploy`.\n- Use `references\u002Ftroubleshooting.md` for backend\u002Fmodel mismatches, optional dependency failures, QLoRA limitations, multimodal OOM, `vllm_limit_mm_per_prompt`, result\u002Flogprob surprises, adapter loading, and unreachable local servers.\n- Use `scripts\u002Fbuild_inference_command.py` to print safe `swift infer`, `swift deploy`, or `swift app` command skeletons without launching models.\n- Use `scripts\u002Fsmoke_openai_client.py` to test a local OpenAI-compatible `\u002Fv1\u002Fchat\u002Fcompletions` server; it targets localhost by default and does not use external network resources.\n\n## Use cases covered here\n\n- Interactive text or multimodal CLI inference with `swift infer`.\n- Dataset or batch inference with saved JSONL results and optional metrics\u002Flogprobs.\n- Local Gradio-style inference UI with `swift app`, either self-hosting a model or connecting to an existing base URL.\n- OpenAI-compatible serving with `swift deploy`, including `\u002Fv1\u002Fmodels`, `\u002Fv1\u002Fchat\u002Fcompletions`, `\u002Fv1\u002Fcompletions`, `\u002Fv1\u002Fembeddings`, health\u002Fping, and Swift client calls.\n- Backend selection across `transformers`, `vllm`, `sglang`, and `lmdeploy`, including optional dependency caveats.\n- Full checkpoint, LoRA adapter, merged LoRA, and multiple named LoRA serving plans.\n\n## Reroute boundaries\n\n- Training command construction, checkpoint creation, and LoRA training arguments belong to the training sub-skill.\n- Dataset schema design and custom dataset registration belong to data\u002Fmodel customization.\n- Export, merge-only packaging, quantization, and evaluation pipelines belong to export\u002Fevaluation.\n- GRPO rollout, Ray, and Megatron serving\u002Fsampling internals belong to advanced RL\u002Fdistributed workflows.\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\u002Fms-swift\u002Fsub-skills\u002Finference-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 inference-deployment",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill inference-deployment",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill inference-deployment","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fms-swift\u002Fsub-skills\u002Finference-deployment\u002FSKILL.md",[47,53,57,61,65,71],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fapi-reference.md","REFERENCE","参考文档",9761,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fms-swift\u002Fsub-skills\u002Finference-deployment\u002Freferences\u002Fapi-reference.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fbackend-compatibility.md",9079,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fms-swift\u002Fsub-skills\u002Finference-deployment\u002Freferences\u002Fbackend-compatibility.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",9196,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fms-swift\u002Fsub-skills\u002Finference-deployment\u002Freferences\u002Ftroubleshooting.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Fworkflows.md",11021,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fms-swift\u002Fsub-skills\u002Finference-deployment\u002Freferences\u002Fworkflows.md",{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Fbuild_inference_command.py","SCRIPT","脚本",9595,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fms-swift\u002Fsub-skills\u002Finference-deployment\u002Fscripts\u002Fbuild_inference_command.py",{"path":72,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":73,"sourceHtmlUrl":74},"scripts\u002Fsmoke_openai_client.py",4882,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fms-swift\u002Fsub-skills\u002Finference-deployment\u002Fscripts\u002Fsmoke_openai_client.py",[76,83,90,97,104,111],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"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":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"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":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"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":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"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":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"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":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"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",[],[]]