AGENT SKILL

quantized-modules-functions

Direct use of bitsandbytes quantized PyTorch modules, autograd matmul helpers, and functional quantization primitives for custom modules and research code.

License 许可
MIT
最近更新
2026-09-03
Stars
★ 351
Forks
27

01 前言 Front Matter

name
quantized-modules-functions
license
MIT
metadata
{ "disco-role": "operating" }
description
Direct use of bitsandbytes quantized PyTorch modules, autograd matmul helpers, and functional quantization primitives for custom modules and research code.
disable-model-invocation
true

02 资源文件 4

03 SKILL.md 正文

Quantized Modules and Functional Primitives

Use 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.

Choose this sub-skill for

  • Replacing torch.nn.Linear or torch.nn.Embedding with Linear8bitLt, Linear4bit, LinearNF4, LinearFP4, Embedding8bit, Embedding4bit, EmbeddingNF4, or EmbeddingFP4 in custom PyTorch code.
  • Working directly with Int8Params, Params4bit, QuantState, matmul, matmul_4bit, int8 vectorwise quantization, 4-bit quantization, or blockwise quantization primitives.
  • Debugging direct module state dicts, quantized checkpoints, SCB/CB fields, .to(device) quantization timing, quant_state handling, blocksize rules, or quantized tensor storage dtype.
  • Creating CPU-safe construction/signature checks for agents or CI without requiring quantized GPU kernels.

Route elsewhere

  • Hugging Face BitsAndBytesConfig, load_in_8bit, load_in_4bit, QLoRA model loading, PEFT, Accelerate, Diffusers, and FSDP-QLoRA workflows route to transformers-integrations.
  • Package installation, backend compatibility, missing native library, CUDA/ROCm/XPU/HPU/MPS setup, and python -m bitsandbytes failures route to installation-diagnostics.
  • Adam8bit, AdamW8bit, paged optimizers, GlobalOptimManager, StableEmbedding, and training-loop optimizer behavior route to optimizers-training.

Start here

  1. Read references/api-reference.md for verified constructor/function signatures and parameter notes.
  2. Use references/workflows.md for direct layer replacement, quantize-on-.to(device), save/load caveats, and primitive recipes.
  3. Use references/troubleshooting.md to map common symptoms to recovery steps.
  4. Run scripts/quantized-module-smoke.py for a deterministic CPU-safe import/construction/signature check; pass --device cuda or another backend only when that backend is available and native quantized kernels are expected to work.

04 同仓库更多 Skills

VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-triton-opt

Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block/grid/warp 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.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

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.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-skill

PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under ./pass_dir/, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

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()/replacement_args()/replacement_func() files, when a pass "failed to match", or when deciding how to fuse multiple kernels/ops.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-orchestrate

Round/batch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep/revert 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.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-feedback

Fast, deterministic feedback for PassNet work: pre-flight pattern/match 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).

★ 351