statequant

Recurrent-state quantization for linear-attention and SSM hybrid language models. statequant implements published state-quantization methods (PACE, DAMP, STEPQuant, Q-Mamba DSQ, LRB + BDR, LeapQuant, decay-weighted allocation, ...) behind one interface and runs them on every recurrent-state family with open-weight LLMs: Gated DeltaNet, KDA, Mamba2 / SSD, MiniMax lightning and RWKV-6 / RWKV-7.

• Reference path (transformers / fla): every method on every supported model, for evaluation.
• Packed Triton kernels: int4 / int8 / bf16 state storage with a decode buffer, for Gated DeltaNet, Mamba2 and KDA.
• vLLM plugin: serve Qwen3.5 / Qwen3-Next, OLMo-Hybrid, Nemotron-H-style Mamba2 hybrids and Ling-3.0 with a packed recurrent state.

Installation

pip install statequant              # core (torch)
pip install "statequant[hf]"        # + transformers, for the reference path
pip install "statequant[hf,fla]"    # + flash-linear-attention kernels (GPU)
pip install "statequant[vllm]"      # + vLLM, for the serving plugin

Quickstart

import statequant as sq

q = sq.pace4()                           # or sq.pace48(), sq.damp_int8(), sq.lrb_bdr(), sq.leapquant(8), ...
sq.calibrate(model, q, calib_ids)        # only for methods with a fitted allocation
with sq.apply(model, q):                 # the method's published rounding schedule
    out = model.generate(ids, max_new_tokens=256)
print(sq.report(model, q))               # bits per state value, MiB per sequence

Serving with vLLM:

STATEQUANT_VLLM=pace4 vllm serve Qwen/Qwen3.5-4B --no-enable-prefix-caching

Implemented methods

Formats, schedules and how to compose your own: docs/methods.md. Per-model quality of every method: docs/results.md.

Supported models

Details per family, method coverage and model-specific notes: docs/models.md.

Results

vLLM 0.32 end to end, packed state vs stock:

Decode-step latency of the packed kernels:

Full tables and setups: docs/results.md.

Documentation

• Methods: presets, formats, schedules, stateful methods
• Supported models: support matrix, per-family notes
• Packed kernels: storage layout, fused decode step, tests, latency
• vLLM plugin: configuration, restrictions, end-to-end checks
• Results: every preset per model

Citation

If you use statequant, please cite:

@article{haller2026pace,
  title   = {{PACE}: Periodic and Channel-Aligned Encoding of Four-Bit Recurrent States},
  author  = {Haller, Patrick and Laitenberger, Filipe and Akbik, Alan},
  journal = {arXiv preprint arXiv:2610.29545},
  year    = {2026}
}

@software{haller2026statequant,
  title   = {statequant: Recurrent-State Quantization for Hybrid Language Models},
  author  = {Haller, Patrick},
  url     = {https://github.com/HallerPatrick/StateQuant},
  version = {0.1.0},
  year    = {2026}
}

Please also cite the papers of the methods you use (listed in docs/methods.md).

License

Apache-2.0. See LICENSE.