[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78ZGK2PHTEHJWB88DCK3W2Y":3,"skill-same:01M78ZGK2PHTEHJWB88DCK3W2Y":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},"01M78ZGK2PHTEHJWB88DCK3W2Y","serving-apis",null,"Serve LMDeploy models through OpenAI-compatible, Responses-compatible, Anthropic-compatible, proxy, and client integration APIs.","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\u002Flmdeploy\u002Fsub-skills\u002Fserving-apis\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: serving-apis\ndescription: \"Serve LMDeploy models through OpenAI-compatible,\n  Responses-compatible, Anthropic-compatible, proxy, and client integration\n  APIs.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Serving APIs\n\nUse this sub-skill when the task is to expose an LMDeploy model as a network service or connect an OpenAI\u002FResponses\u002FAnthropic-style client to that service.\n\n## Route Here\n\n- Build `lmdeploy serve api_server` commands, including `--server-name`, `--server-port`, `--model-name`, `--backend`, `--tp`, cache\u002Fsession flags, `--api-keys`, `--ssl`, docs, and parser flags.\n- Operate `lmdeploy serve proxy` for multiple `api_server` nodes and route OpenAI-compatible traffic through the proxy.\n- Call `\u002Fv1\u002Fmodels`, `\u002Fv1\u002Fchat\u002Fcompletions`, `\u002Fv1\u002Fcompletions`, `\u002Fv1\u002Fresponses`, `\u002Fv1\u002Fmessages`, and `\u002Fv1\u002Fmessages\u002Fcount_tokens`.\n- Use `lmdeploy.serve.openai.api_client.APIClient`, the OpenAI Python SDK, Codex Responses integration, Claude Code Anthropic integration, or `curl`.\n- Configure `--tool-call-parser` and `--reasoning-parser` for tool-call and reasoning output extraction.\n\n## Route Elsewhere\n\n- Offline local text inference belongs in `pipeline-inference`.\n- Multimodal message\u002Fimage\u002Fvideo payload details belong in `vision-language`.\n- Creating AWQ\u002FGPTQ\u002FSmoothQuant\u002Fother quantized artifacts belongs in `quantization`.\n- Deep backend performance tuning, new-model support, kernel behavior, or backend config internals belong in `backend-extension`.\n\n## Quick Start\n\n```bash\nlmdeploy serve api_server \u003Cmodel-or-path> \\\n  --backend pytorch \\\n  --server-name 0.0.0.0 \\\n  --server-port 23333 \\\n  --model-name lmdeploy-model \\\n  --tp 1\n```\n\nValidate the exposed model and chat endpoint:\n\n```bash\ncurl http:\u002F\u002F127.0.0.1:23333\u002Fv1\u002Fmodels\ncurl http:\u002F\u002F127.0.0.1:23333\u002Fv1\u002Fchat\u002Fcompletions \\\n  -H \"content-type: application\u002Fjson\" \\\n  -d '{\"model\":\"lmdeploy-model\",\"messages\":[{\"role\":\"user\",\"content\":\"Reply with pong\"}],\"max_tokens\":32}'\n```\n\nIf launched with `--api-keys my-secret`, add `-H \"Authorization: Bearer my-secret\"` to client requests.\n\n## References\n\n- `references\u002Fcli-reference.md`: command construction for `api_server` and `proxy`.\n- `references\u002Fapi-reference.md`: endpoint contracts and request\u002Fresponse notes.\n- `references\u002Fclient-integration.md`: `APIClient`, OpenAI SDK, Codex, Claude Code, and validation curls.\n- `references\u002Ftroubleshooting.md`: symptoms, causes, and recovery steps.\n- `scripts\u002Fcheck_server_contract.py`: offline\u002Foptional-live contract checker for base URLs and endpoint shape.\n\n## Validation Pattern\n\n1. Run `lmdeploy serve api_server --help` and `lmdeploy serve proxy --help` to verify installed CLI flags.\n2. Start `api_server` with an explicit `--model-name` and any needed parser\u002Fauth flags.\n3. Run `python scripts\u002Fcheck_server_contract.py --base-url http:\u002F\u002F127.0.0.1:23333 --model \u003Cmodel-name>` for offline request preview.\n4. Add `--probe` to perform live `\u002Fv1\u002Fmodels`, chat, completions, Responses, and Anthropic contract probes.\n","# Serving APIs\n\nUse this sub-skill when the task is to expose an LMDeploy model as a network service or connect an OpenAI\u002FResponses\u002FAnthropic-style client to that service.\n\n## Route Here\n\n- Build `lmdeploy serve api_server` commands, including `--server-name`, `--server-port`, `--model-name`, `--backend`, `--tp`, cache\u002Fsession flags, `--api-keys`, `--ssl`, docs, and parser flags.\n- Operate `lmdeploy serve proxy` for multiple `api_server` nodes and route OpenAI-compatible traffic through the proxy.\n- Call `\u002Fv1\u002Fmodels`, `\u002Fv1\u002Fchat\u002Fcompletions`, `\u002Fv1\u002Fcompletions`, `\u002Fv1\u002Fresponses`, `\u002Fv1\u002Fmessages`, and `\u002Fv1\u002Fmessages\u002Fcount_tokens`.\n- Use `lmdeploy.serve.openai.api_client.APIClient`, the OpenAI Python SDK, Codex Responses integration, Claude Code Anthropic integration, or `curl`.\n- Configure `--tool-call-parser` and `--reasoning-parser` for tool-call and reasoning output extraction.\n\n## Route Elsewhere\n\n- Offline local text inference belongs in `pipeline-inference`.\n- Multimodal message\u002Fimage\u002Fvideo payload details belong in `vision-language`.\n- Creating AWQ\u002FGPTQ\u002FSmoothQuant\u002Fother quantized artifacts belongs in `quantization`.\n- Deep backend performance tuning, new-model support, kernel behavior, or backend config internals belong in `backend-extension`.\n\n## Quick Start\n\n```bash\nlmdeploy serve api_server \u003Cmodel-or-path> \\\n  --backend pytorch \\\n  --server-name 0.0.0.0 \\\n  --server-port 23333 \\\n  --model-name lmdeploy-model \\\n  --tp 1\n```\n\nValidate the exposed model and chat endpoint:\n\n```bash\ncurl http:\u002F\u002F127.0.0.1:23333\u002Fv1\u002Fmodels\ncurl http:\u002F\u002F127.0.0.1:23333\u002Fv1\u002Fchat\u002Fcompletions \\\n  -H \"content-type: application\u002Fjson\" \\\n  -d '{\"model\":\"lmdeploy-model\",\"messages\":[{\"role\":\"user\",\"content\":\"Reply with pong\"}],\"max_tokens\":32}'\n```\n\nIf launched with `--api-keys my-secret`, add `-H \"Authorization: Bearer my-secret\"` to client requests.\n\n## References\n\n- `references\u002Fcli-reference.md`: command construction for `api_server` and `proxy`.\n- `references\u002Fapi-reference.md`: endpoint contracts and request\u002Fresponse notes.\n- `references\u002Fclient-integration.md`: `APIClient`, OpenAI SDK, Codex, Claude Code, and validation curls.\n- `references\u002Ftroubleshooting.md`: symptoms, causes, and recovery steps.\n- `scripts\u002Fcheck_server_contract.py`: offline\u002Foptional-live contract checker for base URLs and endpoint shape.\n\n## Validation Pattern\n\n1. Run `lmdeploy serve api_server --help` and `lmdeploy serve proxy --help` to verify installed CLI flags.\n2. Start `api_server` with an explicit `--model-name` and any needed parser\u002Fauth flags.\n3. Run `python scripts\u002Fcheck_server_contract.py --base-url http:\u002F\u002F127.0.0.1:23333 --model \u003Cmodel-name>` for offline request preview.\n4. Add `--probe` to perform live `\u002Fv1\u002Fmodels`, chat, completions, Responses, and Anthropic contract probes.\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\u002Flmdeploy\u002Fsub-skills\u002Fserving-apis",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 serving-apis",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill serving-apis",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill serving-apis","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flmdeploy\u002Fsub-skills\u002Fserving-apis\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",6340,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flmdeploy\u002Fsub-skills\u002Fserving-apis\u002Freferences\u002Fapi-reference.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fcli-reference.md",6017,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flmdeploy\u002Fsub-skills\u002Fserving-apis\u002Freferences\u002Fcli-reference.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fclient-integration.md",6912,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flmdeploy\u002Fsub-skills\u002Fserving-apis\u002Freferences\u002Fclient-integration.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Ftroubleshooting.md",6797,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flmdeploy\u002Fsub-skills\u002Fserving-apis\u002Freferences\u002Ftroubleshooting.md",{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Fcheck_server_contract.py","SCRIPT","脚本",7454,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flmdeploy\u002Fsub-skills\u002Fserving-apis\u002Fscripts\u002Fcheck_server_contract.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",[],[]]