AGENT SKILL

scalar-quantizers

Operate FSQ, FSP, ResidualFSQ, and GroupedResidualFSQ scalar quantizers in vector-quantize-pytorch.

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

01 前言 Front Matter

name
scalar-quantizers
license
MIT
metadata
{ "disco-role": "operating" }
description
Operate FSQ, FSP, ResidualFSQ, and GroupedResidualFSQ scalar quantizers in vector-quantize-pytorch.
disable-model-invocation
true

02 资源文件 4

03 SKILL.md 正文

Scalar Quantizers

Use this sub-skill when a task needs scalar discretization in vector-quantize-pytorch: finite scalar quantization, finite scalar perturbation, residual scalar quantizers, grouped residual scalar quantizers, index roundtrips, tensor-layout decisions, or scalar-quantizer troubleshooting.

Route here for

  • FSQ setup with levels, dim, num_codebooks, return_indices, channel_first, preserve_symmetry, bound_hard_clamp, orthogonal_rotation, projections, and index conversion.
  • FSP setup with levels, dim, channel_first, act_name, quantize_rate, need_inv_act, vector_norm, four-value return tuples, stochastic training perturbation, and eval-time roundtrips.
  • ResidualFSQ and GroupedResidualFSQ for residual stacks, grouped feature splits, num_quantizers, residual reconstruction from indices, return_all_codes, and quantize-dropout caveats.
  • Debugging shape, dtype, projection, activation, norm, and exact-vs-allclose reconstruction issues in scalar quantizers.

Route elsewhere

  • Use the top-level skill to choose package installation and overall routing.
  • Use ../vector-quantization/ for learned codebook VectorQuantize, RandomProjectionQuantizer, codebook EMA, masks, and top-k/manual EMA updates.
  • Use ../residual-quantizers/ for ResidualVQ and GroupedResidualVQ learned-codebook residual workflows.
  • Use ../lookup-free-and-latent/ for LFQ, ResidualLFQ, GroupedResidualLFQ, LatentQuantize, binary entropy losses, and lookup-free/latent quantization.
  • Use ../sim-and-hierarchical/ for SimVQ, ResidualSimVQ, and HierarchicalVQ.

Required references

Read these bundled references before implementing or debugging a scalar workflow:

  1. references/api-reference.md for constructor signatures, return tuples, shape contracts, index helpers, projections, and dtype behavior.
  2. references/workflows.md for safe FSQ/FSP/residual recipes and code patterns.
  3. references/troubleshooting.md for common errors, unsupported settings, roundtrip caveats, and precision/layout fixes.

Safe smoke helper

Run the bundled helper when you need a quick CPU sanity check of the installed package and the scalar APIs:

python scripts/smoke_scalar_quantizers.py --help
python scripts/smoke_scalar_quantizers.py

The helper uses small random tensors only. It does not download datasets, train MNIST models, or depend on any source tree.

Operating cautions

  • FSQ returns exactly two values: (quantized, indices). If return_indices=False, the second value is None and index roundtrip helpers are unavailable for that instance.
  • FSP returns exactly four values: (quantized, indices, norm_loss, other_info).
  • Prefer eval mode and torch.allclose for reconstruction checks that involve FSP, projections, autocast, or low precision. Exact equality is reliable only for the narrow deterministic cases called out in the API reference.
  • For image-like tensors, confirm whether the class expects channel-first handling. FSQ treats 4D+ inputs as channel-first feature maps; FSP requires channel_first=True for NCHW-style inputs.

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