[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M792CBAMRG9JVRK212THSN1G":3,"skill-same:01M792CBAMRG9JVRK212THSN1G":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},"01M792CBAMRG9JVRK212THSN1G","deployment-serving",null,"Use PaddleSpeech server\u002Fclient, HTTP and WebSocket APIs, offline and streaming configs, Paddle Inference, ONNX, C++ runtime, and deployment troubleshooting safely.","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\u002Fpaddlespeech\u002Fsub-skills\u002Fdeployment-serving\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: deployment-serving\ndescription: \"Use PaddleSpeech server\u002Fclient, HTTP and WebSocket APIs, offline\n  and streaming configs, Paddle Inference, ONNX, C++ runtime, and deployment\n  troubleshooting safely.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Deployment and Serving\n\nUse this sub-skill for `paddlespeech_server`, `paddlespeech_client`, PaddleSpeech Serving config YAML, HTTP REST APIs, WebSocket streaming ASR\u002FTTS, online TTS, ACS, Paddle Inference\u002Fstatic models, ONNX streaming, C++ runtime, mobile\u002FARM deployment orientation, and service troubleshooting.\n\n## Safe Serving Workflow\n\n1. Inspect the config before launch:\n\n   ```bash\n   python scripts\u002Finspect_server_config.py --config application.yaml\n   ```\n\n2. Confirm side effects: server startup downloads\u002Fwarmups models, opens ports, and runs until stopped.\n3. Start only after approval:\n\n   ```bash\n   paddlespeech_server start --config_file application.yaml\n   ```\n\n4. Use the matching client:\n\n   ```bash\n   paddlespeech_client asr --server_ip 127.0.0.1 --port 8090 --input input_16k.wav\n   paddlespeech_client tts --server_ip 127.0.0.1 --port 8090 --input \"您好\" --output output.wav\n   paddlespeech_client tts_online --server_ip 127.0.0.1 --port 8092 --protocol http --input \"您好\" --output output.wav\n   ```\n\n## Route by Deployment Surface\n\n- **Offline HTTP ASR\u002FTTS\u002FCLS\u002FTEXT\u002FVECTOR\u002FACS**: read `references\u002Fserver-and-streaming.md` and `references\u002Fapi-contracts.md`.\n- **Streaming ASR**: WebSocket-only ASR endpoint; use a WebSocket config and `paddlespeech_client asr_online`.\n- **Streaming TTS**: HTTP or WebSocket depending on `protocol`; online or online-ONNX engine types.\n- **Paddle Inference\u002Fstatic**: use static model configs and predictor sections; do not mix dynamic checkpoints.\n- **C++\u002Fmobile\u002FAndroid\u002FARM\u002FFastDeploy**: read `references\u002Fruntime-deployment.md`; treat builds as toolchain workflows requiring approval.\n- **Audio search \u002F ACS \u002F Milvus apps**: use this sub-skill for service boundaries and external service planning; route embedding details to `..\u002Faudio-analysis\u002FSKILL.md`.\n\n## References and Helper\n\n- `references\u002Fserver-and-streaming.md` explains config fields, engine lists, protocols, and client commands.\n- `references\u002Fapi-contracts.md` summarizes REST and WebSocket routes and payload expectations.\n- `references\u002Fruntime-deployment.md` covers static\u002FPaddle Inference, ONNX, C++ runtime, Android\u002FARM, Docker, and audio-search boundaries.\n- `references\u002Ftroubleshooting.md` covers ports, host binding, protocol mismatch, engine warmup, and service dependencies.\n- `scripts\u002Finspect_server_config.py` safely validates YAML structure without starting a server.\n\n## Do Not Do by Default\n\n- Do not start server processes, Docker Compose, Milvus\u002FMySQL, C++ builds, Android\u002FARM builds, or streaming demos without approval.\n- Do not claim server readiness from CLI help; warmup and model downloads are separate runtime checks.\n- Do not use HTTP clients against WebSocket streaming ASR configs or offline configs against online engine types.\n","# Deployment and Serving\n\nUse this sub-skill for `paddlespeech_server`, `paddlespeech_client`, PaddleSpeech Serving config YAML, HTTP REST APIs, WebSocket streaming ASR\u002FTTS, online TTS, ACS, Paddle Inference\u002Fstatic models, ONNX streaming, C++ runtime, mobile\u002FARM deployment orientation, and service troubleshooting.\n\n## Safe Serving Workflow\n\n1. Inspect the config before launch:\n\n   ```bash\n   python scripts\u002Finspect_server_config.py --config application.yaml\n   ```\n\n2. Confirm side effects: server startup downloads\u002Fwarmups models, opens ports, and runs until stopped.\n3. Start only after approval:\n\n   ```bash\n   paddlespeech_server start --config_file application.yaml\n   ```\n\n4. Use the matching client:\n\n   ```bash\n   paddlespeech_client asr --server_ip 127.0.0.1 --port 8090 --input input_16k.wav\n   paddlespeech_client tts --server_ip 127.0.0.1 --port 8090 --input \"您好\" --output output.wav\n   paddlespeech_client tts_online --server_ip 127.0.0.1 --port 8092 --protocol http --input \"您好\" --output output.wav\n   ```\n\n## Route by Deployment Surface\n\n- **Offline HTTP ASR\u002FTTS\u002FCLS\u002FTEXT\u002FVECTOR\u002FACS**: read `references\u002Fserver-and-streaming.md` and `references\u002Fapi-contracts.md`.\n- **Streaming ASR**: WebSocket-only ASR endpoint; use a WebSocket config and `paddlespeech_client asr_online`.\n- **Streaming TTS**: HTTP or WebSocket depending on `protocol`; online or online-ONNX engine types.\n- **Paddle Inference\u002Fstatic**: use static model configs and predictor sections; do not mix dynamic checkpoints.\n- **C++\u002Fmobile\u002FAndroid\u002FARM\u002FFastDeploy**: read `references\u002Fruntime-deployment.md`; treat builds as toolchain workflows requiring approval.\n- **Audio search \u002F ACS \u002F Milvus apps**: use this sub-skill for service boundaries and external service planning; route embedding details to `..\u002Faudio-analysis\u002FSKILL.md`.\n\n## References and Helper\n\n- `references\u002Fserver-and-streaming.md` explains config fields, engine lists, protocols, and client commands.\n- `references\u002Fapi-contracts.md` summarizes REST and WebSocket routes and payload expectations.\n- `references\u002Fruntime-deployment.md` covers static\u002FPaddle Inference, ONNX, C++ runtime, Android\u002FARM, Docker, and audio-search boundaries.\n- `references\u002Ftroubleshooting.md` covers ports, host binding, protocol mismatch, engine warmup, and service dependencies.\n- `scripts\u002Finspect_server_config.py` safely validates YAML structure without starting a server.\n\n## Do Not Do by Default\n\n- Do not start server processes, Docker Compose, Milvus\u002FMySQL, C++ builds, Android\u002FARM builds, or streaming demos without approval.\n- Do not claim server readiness from CLI help; warmup and model downloads are separate runtime checks.\n- Do not use HTTP clients against WebSocket streaming ASR configs or offline configs against online engine types.\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\u002Fpaddlespeech\u002Fsub-skills\u002Fdeployment-serving",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-serving",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill deployment-serving",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill deployment-serving","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpaddlespeech\u002Fsub-skills\u002Fdeployment-serving\u002FSKILL.md",[47,53,57,61,65],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fapi-contracts.md","REFERENCE","参考文档",2156,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpaddlespeech\u002Fsub-skills\u002Fdeployment-serving\u002Freferences\u002Fapi-contracts.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fruntime-deployment.md",1835,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpaddlespeech\u002Fsub-skills\u002Fdeployment-serving\u002Freferences\u002Fruntime-deployment.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fserver-and-streaming.md",2313,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpaddlespeech\u002Fsub-skills\u002Fdeployment-serving\u002Freferences\u002Fserver-and-streaming.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Ftroubleshooting.md",1482,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpaddlespeech\u002Fsub-skills\u002Fdeployment-serving\u002Freferences\u002Ftroubleshooting.md",{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Finspect_server_config.py","SCRIPT","脚本",2790,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpaddlespeech\u002Fsub-skills\u002Fdeployment-serving\u002Fscripts\u002Finspect_server_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",[],[]]