[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78WMH02V1FAQ2PR8FXFW1Z6":3,"skill-same:01M78WMH02V1FAQ2PR8FXFW1Z6":61},{"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},"01M78WMH02V1FAQ2PR8FXFW1Z6","export-and-optimization",null,"Routes EasyCV export, pruning, quantization, TorchAccelerator, and inference-optimization 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\u002Feasycv\u002Fsub-skills\u002Fexport-and-optimization\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: export-and-optimization\ndescription: \"Routes EasyCV export, pruning, quantization, TorchAccelerator, and\n  inference-optimization workflows.\"\nmetadata:\n  disco-role: operating\ndisable-model-invocation: true\nlicense: Apache 2.0\n---\n\n# Export and optimization\n\nUse this sub-skill when the task is to package, speed up, compress, prune, or otherwise optimize an EasyCV checkpoint for inference.\n\nIt covers the export front door, the compression utilities, and the advanced backend-dependent optimization paths.\n\n## Read these references first\n\n- `references\u002Fexport.md` for raw \u002F JIT \u002F Blade \u002F ONNX export behavior and artifact naming.\n- `references\u002Foptimization.md` for pruning, quantization, TorchAccelerator, and analysis helpers.\n- `references\u002Ftroubleshooting.md` for missing extras, backend mismatches, and export-format issues.\n- Root `references\u002Fcli-reference.md` for the installed-package command front doors.\n\n## What belongs here\n\nInclude tasks such as:\n\n- exporting a checkpoint for inference consumption\n- choosing raw, JIT, Blade, or ONNX export behavior\n- keeping preprocess \u002F postprocess sidecars together with the exported model\n- pruning or quantizing a YOLOX-style model\n- using TorchAccelerator-specific configs or runtime notes\n- checking FLOPs, parameters, or inference time with the repo analysis helpers\n\n## What stays elsewhere\n\n- Training or finetuning the source checkpoint -> `sub-skills\u002Ftraining-and-evaluation\u002F`\n- Running the exported artifact on files or tables -> `sub-skills\u002Fprediction-and-inference\u002F`\n- Dataset layout and conversion helpers -> `sub-skills\u002Fdata-preparation\u002F`\n\n## Typical decision flow\n\n1. Decide whether the model should stay raw or be exported for inference.\n2. Check whether the target environment has the backend package for the chosen optimization path.\n3. Choose the export format and any preprocess \u002F postprocess wrapping.\n4. Keep the exported sidecar files together.\n5. For pruning or quantization, confirm the extra dependency stack before you start.\n\n## Common success signals\n\n- The export command writes the expected model file and sidecars.\n- The exported artifact reloads with the corresponding predictor class.\n- Optional optimization dependencies are installed only for the paths that need them.\n- The output format matches the predictor path that will consume it later.\n\n## Common optimization surfaces\n\n- `blade_compression` and `pai_nni` are optional extras for advanced compression flows.\n- `onnxruntime` is needed for ONNX consumption paths.\n- `torchacc` requires the documented CUDA runtime and container path.\n- Exported JIT \u002F Blade models may need a matching `test_pipeline` or preprocess artifact.\n\n","# Export and optimization\n\nUse this sub-skill when the task is to package, speed up, compress, prune, or otherwise optimize an EasyCV checkpoint for inference.\n\nIt covers the export front door, the compression utilities, and the advanced backend-dependent optimization paths.\n\n## Read these references first\n\n- `references\u002Fexport.md` for raw \u002F JIT \u002F Blade \u002F ONNX export behavior and artifact naming.\n- `references\u002Foptimization.md` for pruning, quantization, TorchAccelerator, and analysis helpers.\n- `references\u002Ftroubleshooting.md` for missing extras, backend mismatches, and export-format issues.\n- Root `references\u002Fcli-reference.md` for the installed-package command front doors.\n\n## What belongs here\n\nInclude tasks such as:\n\n- exporting a checkpoint for inference consumption\n- choosing raw, JIT, Blade, or ONNX export behavior\n- keeping preprocess \u002F postprocess sidecars together with the exported model\n- pruning or quantizing a YOLOX-style model\n- using TorchAccelerator-specific configs or runtime notes\n- checking FLOPs, parameters, or inference time with the repo analysis helpers\n\n## What stays elsewhere\n\n- Training or finetuning the source checkpoint -> `sub-skills\u002Ftraining-and-evaluation\u002F`\n- Running the exported artifact on files or tables -> `sub-skills\u002Fprediction-and-inference\u002F`\n- Dataset layout and conversion helpers -> `sub-skills\u002Fdata-preparation\u002F`\n\n## Typical decision flow\n\n1. Decide whether the model should stay raw or be exported for inference.\n2. Check whether the target environment has the backend package for the chosen optimization path.\n3. Choose the export format and any preprocess \u002F postprocess wrapping.\n4. Keep the exported sidecar files together.\n5. For pruning or quantization, confirm the extra dependency stack before you start.\n\n## Common success signals\n\n- The export command writes the expected model file and sidecars.\n- The exported artifact reloads with the corresponding predictor class.\n- Optional optimization dependencies are installed only for the paths that need them.\n- The output format matches the predictor path that will consume it later.\n\n## Common optimization surfaces\n\n- `blade_compression` and `pai_nni` are optional extras for advanced compression flows.\n- `onnxruntime` is needed for ONNX consumption paths.\n- `torchacc` requires the documented CUDA runtime and container path.\n- Exported JIT \u002F Blade models may need a matching `test_pipeline` or preprocess artifact.\n\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\u002Feasycv\u002Fsub-skills\u002Fexport-and-optimization",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 export-and-optimization",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill export-and-optimization",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill export-and-optimization","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Feasycv\u002Fsub-skills\u002Fexport-and-optimization\u002FSKILL.md",[47,53,57],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fexport.md","REFERENCE","参考文档",1549,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Feasycv\u002Fsub-skills\u002Fexport-and-optimization\u002Freferences\u002Fexport.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Foptimization.md",1618,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Feasycv\u002Fsub-skills\u002Fexport-and-optimization\u002Freferences\u002Foptimization.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",1441,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Feasycv\u002Fsub-skills\u002Fexport-and-optimization\u002Freferences\u002Ftroubleshooting.md",[62,69,76,83,90,97],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"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":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"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":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},"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":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},"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":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},"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":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},"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",[],[]]