[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78ZGMW9MN686X0J6C3ECPMA":3,"skill-same:01M78ZGMW9MN686X0J6C3ECPMA":67},{"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},"01M78ZGMW9MN686X0J6C3ECPMA","vision-language",null,"Use LMDeploy vision-language and multimodal APIs for media loading, VLM prompt formats, OpenAI-style multimodal payloads, image token placement, and no-download media validation.","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\u002Fvision-language\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: vision-language\ndescription: \"Use LMDeploy vision-language and multimodal APIs for media\n  loading, VLM prompt formats, OpenAI-style multimodal payloads, image token\n  placement, and no-download media validation.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Vision Language\n\nUse this sub-skill when the task involves LMDeploy VLM or multimodal inputs: images, videos, audio, time series, OpenAI `content` lists, tuple prompts such as `(prompt, image)`, or `VisionConfig`.\n\n## Read First\n\n- `references\u002Finput-formats.md` for tuple prompts, OpenAI-style content blocks, media URL\u002Fdata URL formats, batch shapes, multi-turn image chat, `IMAGE_TOKEN`, and modality support.\n- `references\u002Fworkflows.md` for copy-ready offline VLM pipeline patterns, API payload construction, base64\u002Flocal media handling, `VisionConfig`, `mm_processor_kwargs`, and payload preflight.\n- `references\u002Ftroubleshooting.md` for optional dependency failures, blocked URLs, fetch timeouts, image token placement, session length, batch media mismatches, chat-template issues, and chemistry\u002Fmedia gaps.\n- `scripts\u002Fcheck_vl_media_inputs.py` for a no-download smoke check that creates a tiny local image, validates base64\u002Fdata URLs, and rejects unsafe URL examples.\n\n## Scope\n\nOwn these tasks:\n\n- Build VLM prompts for `lmdeploy.pipeline`, including `(prompt, image)`, `(prompt, [image1, image2])`, batch prompt lists, and OpenAI-style message lists.\n- Load or encode multimodal media with `lmdeploy.vl.load_image`, `load_video`, `load_audio`, `load_time_series`, and the `encode_*_base64` helpers.\n- Construct OpenAI-compatible multimodal request bodies using `text`, `image_url`, `video_url`, `audio_url`, and `time_series_url` content blocks.\n- Tune VLM-specific inputs with `VisionConfig(max_batch_size=...)`, `media_io_kwargs`, `mm_processor_kwargs`, and manual `IMAGE_TOKEN` placement where model docs require it.\n- Preflight payloads for safe media URL schemes, local\u002Fbase64 media syntax, multiple images, and server-side multimodal parser expectations without downloading model weights.\n\nRoute elsewhere:\n\n- Text-only offline generation, `GenerationConfig` basics, streaming, logits, PPL, and `lmdeploy chat`: `pipeline-inference`.\n- Launching API servers\u002Fproxies, auth, API clients, endpoint routing, and transport operations: `serving-apis`.\n- Creating AWQ\u002FGPTQ\u002FSmoothQuant or other quantized VLM artifacts: `quantization`.\n- Adding or debugging VLM model implementation internals, processor classes, backend kernels, or architecture registration: `backend-extension`.\n\n## Fast Start\n\n```python\nfrom lmdeploy import TurbomindEngineConfig, VisionConfig, pipeline\nfrom lmdeploy.vl import load_image\n\nbackend_config = TurbomindEngineConfig(session_len=8192)\nvision_config = VisionConfig(max_batch_size=4)\n\nwith pipeline(\"org\u002Fvlm-or-local-folder\", backend_config=backend_config, vision_config=vision_config) as pipe:\n    image = load_image(\"\u002Fpath\u002Fto\u002Fimage.jpg\")\n    response = pipe((\"Describe this image.\", image))\n    print(response.text if hasattr(response, \"text\") else response)\n```\n\nFor custom local VLM folder names that LMDeploy cannot map to a built-in template, pass `chat_template_config=ChatTemplateConfig(model_name=\"template-name\")` when creating the pipeline.\n\n## Validation\n\nRun the bundled check before recommending a VLM media workflow:\n\n```bash\npython sub-skills\u002Fvision-language\u002Fscripts\u002Fcheck_vl_media_inputs.py --print-examples\n```\n\nThis check does not download models or fetch remote media. Model execution still requires the user’s selected VLM weights, backend dependencies, accelerator memory, and any model-specific optional packages.\n","# Vision Language\n\nUse this sub-skill when the task involves LMDeploy VLM or multimodal inputs: images, videos, audio, time series, OpenAI `content` lists, tuple prompts such as `(prompt, image)`, or `VisionConfig`.\n\n## Read First\n\n- `references\u002Finput-formats.md` for tuple prompts, OpenAI-style content blocks, media URL\u002Fdata URL formats, batch shapes, multi-turn image chat, `IMAGE_TOKEN`, and modality support.\n- `references\u002Fworkflows.md` for copy-ready offline VLM pipeline patterns, API payload construction, base64\u002Flocal media handling, `VisionConfig`, `mm_processor_kwargs`, and payload preflight.\n- `references\u002Ftroubleshooting.md` for optional dependency failures, blocked URLs, fetch timeouts, image token placement, session length, batch media mismatches, chat-template issues, and chemistry\u002Fmedia gaps.\n- `scripts\u002Fcheck_vl_media_inputs.py` for a no-download smoke check that creates a tiny local image, validates base64\u002Fdata URLs, and rejects unsafe URL examples.\n\n## Scope\n\nOwn these tasks:\n\n- Build VLM prompts for `lmdeploy.pipeline`, including `(prompt, image)`, `(prompt, [image1, image2])`, batch prompt lists, and OpenAI-style message lists.\n- Load or encode multimodal media with `lmdeploy.vl.load_image`, `load_video`, `load_audio`, `load_time_series`, and the `encode_*_base64` helpers.\n- Construct OpenAI-compatible multimodal request bodies using `text`, `image_url`, `video_url`, `audio_url`, and `time_series_url` content blocks.\n- Tune VLM-specific inputs with `VisionConfig(max_batch_size=...)`, `media_io_kwargs`, `mm_processor_kwargs`, and manual `IMAGE_TOKEN` placement where model docs require it.\n- Preflight payloads for safe media URL schemes, local\u002Fbase64 media syntax, multiple images, and server-side multimodal parser expectations without downloading model weights.\n\nRoute elsewhere:\n\n- Text-only offline generation, `GenerationConfig` basics, streaming, logits, PPL, and `lmdeploy chat`: `pipeline-inference`.\n- Launching API servers\u002Fproxies, auth, API clients, endpoint routing, and transport operations: `serving-apis`.\n- Creating AWQ\u002FGPTQ\u002FSmoothQuant or other quantized VLM artifacts: `quantization`.\n- Adding or debugging VLM model implementation internals, processor classes, backend kernels, or architecture registration: `backend-extension`.\n\n## Fast Start\n\n```python\nfrom lmdeploy import TurbomindEngineConfig, VisionConfig, pipeline\nfrom lmdeploy.vl import load_image\n\nbackend_config = TurbomindEngineConfig(session_len=8192)\nvision_config = VisionConfig(max_batch_size=4)\n\nwith pipeline(\"org\u002Fvlm-or-local-folder\", backend_config=backend_config, vision_config=vision_config) as pipe:\n    image = load_image(\"\u002Fpath\u002Fto\u002Fimage.jpg\")\n    response = pipe((\"Describe this image.\", image))\n    print(response.text if hasattr(response, \"text\") else response)\n```\n\nFor custom local VLM folder names that LMDeploy cannot map to a built-in template, pass `chat_template_config=ChatTemplateConfig(model_name=\"template-name\")` when creating the pipeline.\n\n## Validation\n\nRun the bundled check before recommending a VLM media workflow:\n\n```bash\npython sub-skills\u002Fvision-language\u002Fscripts\u002Fcheck_vl_media_inputs.py --print-examples\n```\n\nThis check does not download models or fetch remote media. Model execution still requires the user’s selected VLM weights, backend dependencies, accelerator memory, and any model-specific optional packages.\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\u002Fvision-language",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 vision-language",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill vision-language",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill vision-language","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flmdeploy\u002Fsub-skills\u002Fvision-language\u002FSKILL.md",[47,53,57,61],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Finput-formats.md","REFERENCE","参考文档",7049,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flmdeploy\u002Fsub-skills\u002Fvision-language\u002Freferences\u002Finput-formats.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Ftroubleshooting.md",6354,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flmdeploy\u002Fsub-skills\u002Fvision-language\u002Freferences\u002Ftroubleshooting.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fworkflows.md",6626,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flmdeploy\u002Fsub-skills\u002Fvision-language\u002Freferences\u002Fworkflows.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fcheck_vl_media_inputs.py","SCRIPT","脚本",7570,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flmdeploy\u002Fsub-skills\u002Fvision-language\u002Fscripts\u002Fcheck_vl_media_inputs.py",[68,75,82,89,96,103],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"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":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"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":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"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":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"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":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"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":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"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",[],[]]