[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78ZGD3DVATNHJAMNGW6RMWG":3,"skill-same:01M78ZGD3DVATNHJAMNGW6RMWG":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},"01M78ZGD3DVATNHJAMNGW6RMWG","pipeline-inference",null,"Use LMDeploy pipeline APIs and chat CLI for offline text LLM inference, streaming, sessions, generation settings, backend configs, and chat templates.","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\u002Fpipeline-inference\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: pipeline-inference\ndescription: \"Use LMDeploy pipeline APIs and chat CLI for offline text LLM\n  inference, streaming, sessions, generation settings, backend configs, and chat\n  templates.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Pipeline Inference\n\nUse this sub-skill when the task is offline text LLM inference through `lmdeploy.pipeline`, `Pipeline`, or `lmdeploy chat`.\n\n## Read First\n\n- `references\u002Fapi-reference.md` for exact constructors, methods, response fields, and config defaults.\n- `references\u002Fworkflows.md` for copy-ready offline inference patterns, batch prompts, streaming, sessions, LoRA, logits, hidden states, and PPL.\n- `references\u002Fchat-templates.md` for JSON chat templates, Python registration, prompt-format mismatch diagnosis, and safe inspection.\n- `references\u002Ftroubleshooting.md` for OOM, multiprocessing, missing TurboMind extension, stop-token, model download, and trust boundary failures.\n- `scripts\u002Finspect_pipeline_config.py` for no-download inspection of installed API signatures, dataclass defaults, chat-template registry names, and CLI availability.\n\n## Scope\n\nOwn these tasks:\n\n- Create an offline text pipeline with `from lmdeploy import pipeline` and `TurbomindEngineConfig` or `PytorchEngineConfig`.\n- Run single prompts, batches, OpenAI-style messages, streaming output, and multi-turn chat sessions.\n- Tune `GenerationConfig`, `cache_max_entry_count`, `tp`, `session_len`, `max_batch_size`, LoRA adapters, and chat templates for inference.\n- Inspect logits, last hidden states, token lengths, finish reasons, and PPL without designing a server.\n- Use `lmdeploy chat` for local interactive text inference and CLI smoke checks.\n\nRoute elsewhere:\n\n- Multimodal media loading, image\u002Fvideo prompt construction, and VLM-specific formatting: `vision-language`.\n- REST\u002FgRPC\u002FOpenAI-compatible servers, proxy, API clients, and API-server auth: `serving-apis`.\n- Creating AWQ\u002FGPTQ\u002FSmoothQuant artifacts with `lmdeploy lite`: `quantization`.\n- New architecture patches, backend internals, custom kernels, or model support development: `backend-extension`.\n\n## Fast Start\n\n```python\nfrom lmdeploy import GenerationConfig, TurbomindEngineConfig, pipeline\n\nbackend_config = TurbomindEngineConfig(cache_max_entry_count=0.6, tp=1)\ngen_config = GenerationConfig(max_new_tokens=128, top_p=0.9, temperature=0.7)\n\nwith pipeline(\"org\u002Fmodel-or-local-path\", backend_config=backend_config) as pipe:\n    responses = pipe([\"Explain LMDeploy in one sentence.\", \"List two use cases.\"], gen_config=gen_config)\n    for response in responses:\n        print(response.text)\n```\n\nFor PyTorch backend, use `PytorchEngineConfig(...)`. When `tp > 1` with PyTorch in a script, wrap pipeline creation in `if __name__ == \"__main__\":`.\n\n## Validation\n\nUse these checks before recommending or shipping an offline pipeline workflow:\n\n```bash\npython sub-skills\u002Fpipeline-inference\u002Fscripts\u002Finspect_pipeline_config.py --include-cli\nlmdeploy chat --help\n```\n\nThese checks do not download a model. Model execution requires the user’s chosen model weights, backend dependencies, GPU\u002Faccelerator memory, and any required `trust_remote_code` decision.\n","# Pipeline Inference\n\nUse this sub-skill when the task is offline text LLM inference through `lmdeploy.pipeline`, `Pipeline`, or `lmdeploy chat`.\n\n## Read First\n\n- `references\u002Fapi-reference.md` for exact constructors, methods, response fields, and config defaults.\n- `references\u002Fworkflows.md` for copy-ready offline inference patterns, batch prompts, streaming, sessions, LoRA, logits, hidden states, and PPL.\n- `references\u002Fchat-templates.md` for JSON chat templates, Python registration, prompt-format mismatch diagnosis, and safe inspection.\n- `references\u002Ftroubleshooting.md` for OOM, multiprocessing, missing TurboMind extension, stop-token, model download, and trust boundary failures.\n- `scripts\u002Finspect_pipeline_config.py` for no-download inspection of installed API signatures, dataclass defaults, chat-template registry names, and CLI availability.\n\n## Scope\n\nOwn these tasks:\n\n- Create an offline text pipeline with `from lmdeploy import pipeline` and `TurbomindEngineConfig` or `PytorchEngineConfig`.\n- Run single prompts, batches, OpenAI-style messages, streaming output, and multi-turn chat sessions.\n- Tune `GenerationConfig`, `cache_max_entry_count`, `tp`, `session_len`, `max_batch_size`, LoRA adapters, and chat templates for inference.\n- Inspect logits, last hidden states, token lengths, finish reasons, and PPL without designing a server.\n- Use `lmdeploy chat` for local interactive text inference and CLI smoke checks.\n\nRoute elsewhere:\n\n- Multimodal media loading, image\u002Fvideo prompt construction, and VLM-specific formatting: `vision-language`.\n- REST\u002FgRPC\u002FOpenAI-compatible servers, proxy, API clients, and API-server auth: `serving-apis`.\n- Creating AWQ\u002FGPTQ\u002FSmoothQuant artifacts with `lmdeploy lite`: `quantization`.\n- New architecture patches, backend internals, custom kernels, or model support development: `backend-extension`.\n\n## Fast Start\n\n```python\nfrom lmdeploy import GenerationConfig, TurbomindEngineConfig, pipeline\n\nbackend_config = TurbomindEngineConfig(cache_max_entry_count=0.6, tp=1)\ngen_config = GenerationConfig(max_new_tokens=128, top_p=0.9, temperature=0.7)\n\nwith pipeline(\"org\u002Fmodel-or-local-path\", backend_config=backend_config) as pipe:\n    responses = pipe([\"Explain LMDeploy in one sentence.\", \"List two use cases.\"], gen_config=gen_config)\n    for response in responses:\n        print(response.text)\n```\n\nFor PyTorch backend, use `PytorchEngineConfig(...)`. When `tp > 1` with PyTorch in a script, wrap pipeline creation in `if __name__ == \"__main__\":`.\n\n## Validation\n\nUse these checks before recommending or shipping an offline pipeline workflow:\n\n```bash\npython sub-skills\u002Fpipeline-inference\u002Fscripts\u002Finspect_pipeline_config.py --include-cli\nlmdeploy chat --help\n```\n\nThese checks do not download a model. Model execution requires the user’s chosen model weights, backend dependencies, GPU\u002Faccelerator memory, and any required `trust_remote_code` decision.\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\u002Fpipeline-inference",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 pipeline-inference",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill pipeline-inference",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill pipeline-inference","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flmdeploy\u002Fsub-skills\u002Fpipeline-inference\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",9952,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flmdeploy\u002Fsub-skills\u002Fpipeline-inference\u002Freferences\u002Fapi-reference.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fchat-templates.md",6431,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flmdeploy\u002Fsub-skills\u002Fpipeline-inference\u002Freferences\u002Fchat-templates.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",8030,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flmdeploy\u002Fsub-skills\u002Fpipeline-inference\u002Freferences\u002Ftroubleshooting.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Fworkflows.md",11133,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flmdeploy\u002Fsub-skills\u002Fpipeline-inference\u002Freferences\u002Fworkflows.md",{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Finspect_pipeline_config.py","SCRIPT","脚本",6966,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flmdeploy\u002Fsub-skills\u002Fpipeline-inference\u002Fscripts\u002Finspect_pipeline_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",[],[]]