[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78TDCJSEPR64C2ZENAAVACZ":3,"skill-same:01M78TDCJSEPR64C2ZENAAVACZ":66},{"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":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":32,"install":33,"resources":45},"01M78TDCJSEPR64C2ZENAAVACZ","quantized-modules-functions",null,"Direct use of bitsandbytes quantized PyTorch modules, autograd matmul helpers, and functional quantization primitives for custom modules and research code.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"MIT","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fbitsandbytes\u002Fsub-skills\u002Fquantized-modules-functions\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: quantized-modules-functions\ndescription: \"Direct use of bitsandbytes quantized PyTorch modules, autograd\n  matmul helpers, and functional quantization primitives for custom modules and\n  research code.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Quantized Modules and Functional Primitives\n\nUse this sub-skill when the task needs direct `bitsandbytes.nn`, `bitsandbytes.functional`, `bitsandbytes.matmul`, `bitsandbytes.matmul_4bit`, or `torch.ops.bitsandbytes` APIs rather than Hugging Face model-loading wrappers.\n\n## Choose this sub-skill for\n\n- Replacing `torch.nn.Linear` or `torch.nn.Embedding` with `Linear8bitLt`, `Linear4bit`, `LinearNF4`, `LinearFP4`, `Embedding8bit`, `Embedding4bit`, `EmbeddingNF4`, or `EmbeddingFP4` in custom PyTorch code.\n- Working directly with `Int8Params`, `Params4bit`, `QuantState`, `matmul`, `matmul_4bit`, int8 vectorwise quantization, 4-bit quantization, or blockwise quantization primitives.\n- Debugging direct module state dicts, quantized checkpoints, `SCB`\u002F`CB` fields, `.to(device)` quantization timing, `quant_state` handling, blocksize rules, or quantized tensor storage dtype.\n- Creating CPU-safe construction\u002Fsignature checks for agents or CI without requiring quantized GPU kernels.\n\n## Route elsewhere\n\n- Hugging Face `BitsAndBytesConfig`, `load_in_8bit`, `load_in_4bit`, QLoRA model loading, PEFT, Accelerate, Diffusers, and FSDP-QLoRA workflows route to `transformers-integrations`.\n- Package installation, backend compatibility, missing native library, CUDA\u002FROCm\u002FXPU\u002FHPU\u002FMPS setup, and `python -m bitsandbytes` failures route to `installation-diagnostics`.\n- `Adam8bit`, `AdamW8bit`, paged optimizers, `GlobalOptimManager`, `StableEmbedding`, and training-loop optimizer behavior route to `optimizers-training`.\n\n## Start here\n\n1. Read `references\u002Fapi-reference.md` for verified constructor\u002Ffunction signatures and parameter notes.\n2. Use `references\u002Fworkflows.md` for direct layer replacement, quantize-on-`.to(device)`, save\u002Fload caveats, and primitive recipes.\n3. Use `references\u002Ftroubleshooting.md` to map common symptoms to recovery steps.\n4. Run `scripts\u002Fquantized-module-smoke.py` for a deterministic CPU-safe import\u002Fconstruction\u002Fsignature check; pass `--device cuda` or another backend only when that backend is available and native quantized kernels are expected to work.\n","# Quantized Modules and Functional Primitives\n\nUse this sub-skill when the task needs direct `bitsandbytes.nn`, `bitsandbytes.functional`, `bitsandbytes.matmul`, `bitsandbytes.matmul_4bit`, or `torch.ops.bitsandbytes` APIs rather than Hugging Face model-loading wrappers.\n\n## Choose this sub-skill for\n\n- Replacing `torch.nn.Linear` or `torch.nn.Embedding` with `Linear8bitLt`, `Linear4bit`, `LinearNF4`, `LinearFP4`, `Embedding8bit`, `Embedding4bit`, `EmbeddingNF4`, or `EmbeddingFP4` in custom PyTorch code.\n- Working directly with `Int8Params`, `Params4bit`, `QuantState`, `matmul`, `matmul_4bit`, int8 vectorwise quantization, 4-bit quantization, or blockwise quantization primitives.\n- Debugging direct module state dicts, quantized checkpoints, `SCB`\u002F`CB` fields, `.to(device)` quantization timing, `quant_state` handling, blocksize rules, or quantized tensor storage dtype.\n- Creating CPU-safe construction\u002Fsignature checks for agents or CI without requiring quantized GPU kernels.\n\n## Route elsewhere\n\n- Hugging Face `BitsAndBytesConfig`, `load_in_8bit`, `load_in_4bit`, QLoRA model loading, PEFT, Accelerate, Diffusers, and FSDP-QLoRA workflows route to `transformers-integrations`.\n- Package installation, backend compatibility, missing native library, CUDA\u002FROCm\u002FXPU\u002FHPU\u002FMPS setup, and `python -m bitsandbytes` failures route to `installation-diagnostics`.\n- `Adam8bit`, `AdamW8bit`, paged optimizers, `GlobalOptimManager`, `StableEmbedding`, and training-loop optimizer behavior route to `optimizers-training`.\n\n## Start here\n\n1. Read `references\u002Fapi-reference.md` for verified constructor\u002Ffunction signatures and parameter notes.\n2. Use `references\u002Fworkflows.md` for direct layer replacement, quantize-on-`.to(device)`, save\u002Fload caveats, and primitive recipes.\n3. Use `references\u002Ftroubleshooting.md` to map common symptoms to recovery steps.\n4. Run `scripts\u002Fquantized-module-smoke.py` for a deterministic CPU-safe import\u002Fconstruction\u002Fsignature check; pass `--device cuda` or another backend only when that backend is available and native quantized kernels are expected to work.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fbitsandbytes\u002Fsub-skills\u002Fquantized-modules-functions",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":25},[35,38,41],{"tool":36,"command":37},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill quantized-modules-functions",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill quantized-modules-functions",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill quantized-modules-functions","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fbitsandbytes\u002Fsub-skills\u002Fquantized-modules-functions\u002FSKILL.md",[46,52,56,60],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fapi-reference.md","REFERENCE","参考文档",8634,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fbitsandbytes\u002Fsub-skills\u002Fquantized-modules-functions\u002Freferences\u002Fapi-reference.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Ftroubleshooting.md",6415,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fbitsandbytes\u002Fsub-skills\u002Fquantized-modules-functions\u002Freferences\u002Ftroubleshooting.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fworkflows.md",6430,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fbitsandbytes\u002Fsub-skills\u002Fquantized-modules-functions\u002Freferences\u002Fworkflows.md",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Fquantized-module-smoke.py","SCRIPT","脚本",5356,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fbitsandbytes\u002Fsub-skills\u002Fquantized-modules-functions\u002Fscripts\u002Fquantized-module-smoke.py",[67,75,82,89,96,103],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"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.","Apache-2.0","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":71,"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":71,"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":71,"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":71,"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":71,"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",[],[]]