LoopQ: Quantization for Recursive Transformers

• URL: http://arxiv.org/abs/2605.16343v1
• Date: Fri, 08 May 2026 01:45:28 GMT
• Title: LoopQ: Quantization for Recursive Transformers
• Abstract summary: We present the first systematic study of quantization in LoopLMs.<n>We propose LoopQ, a loop-aware PTQ framework that preserves a shared quantized backbone while introducing lightweight adaptations.<n> Experiments show that, under W4A4 quantization, LoopQ improves average downstream accuracy by 68.8% and reduces average perplexity by 87.7% compared with the strongest static PTQ baseline.
• Score: 14.001192614503807
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Looped language models (LoopLMs) improve parameter efficiency by recursively reusing Transformer blocks, enabling deeper computation under a fixed model size. However, this reuse makes LoopLMs more fragile under post-training quantization (PTQ). We present the first systematic study of quantization in LoopLMs and identify three challenges: distribution shift across roles, state reuse across loop transitions, and recursive error accumulation. To address these challenges, we propose LoopQ, a loop-aware PTQ framework that preserves a shared quantized backbone while introducing lightweight adaptations. LoopQ combines activation scaling, selective transformation, cross-loop state alignment, and trajectory-aware optimization to reduce distributional mismatch within loops and error accumulation across loops. Experiments across seven benchmarks show that, under W4A4 quantization, LoopQ improves average downstream accuracy by 68.8% and reduces average perplexity by 87.7% compared with the strongest static PTQ baseline.

Related papers

• KronQ: LLM Quantization via Kronecker-Factored Hessian [19.710403142085102]
  Post-training quantization (PTQ) is a widely adopted technique for compressing large language models (LLMs) without retraining.<n>We propose KronQ, a PTQ framework that challenges the assumption by introducing the gradient covariance into the quantization pipeline.
  arXiv  Detail & Related papers  (2026-07-08T22:34:52Z)
• Stabilizing Extrapolation in Looped Transformers via Learned Stochastic Stopping [56.14767235650558]
  Looped Transformers, which repeatedly apply a shared transformer block, are an architecturally natural fit for variable-length computation tasks.<n>We trace this variance to the spurious correlation in simple algorithmic tasks between sequence length and number of loops.<n>Our work suggests that "when to stop" should be treated as a training design choice, not merely an inference-time-allocation rule.
  arXiv  Detail & Related papers  (2026-06-29T08:58:09Z)
• LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling [72.71005779366162]
  This study studies loop-count selection through a gain--cost view.<n>We instantiate this study by training LoopCoder-v2 with different loop counts, from scratch on 18T tokens, followed by matched instruction tuning and evaluation.<n> Empirically, the two-loop variant delivers broad gains over the non-looped baseline across code generation, code reasoning, agentic software engineering, and tooluse benchmarks.
  arXiv  Detail & Related papers  (2026-06-16T15:03:05Z)
• RUQuant: Towards Refining Uniform Quantization for Large Language Models [17.258420059228808]
  Post-training quantization (PTQ) has emerged as a practical solution by compressing models without requiring retraining.<n>Existing methods often suffer from substantial accuracy degradation due to the non-uniform nature of activation distributions.<n>In this work, we revisit the activation quantization problem from a theoretical perspective grounded in the Lloyd-Max optimality conditions.
  arXiv  Detail & Related papers  (2026-04-05T08:04:39Z)
• BPDQ: Bit-Plane Decomposition Quantization on a Variable Grid for Large Language Models [56.504879072674015]
  We propose Bit-Plane Decomposition Quantization (BPDQ), which constructs a variable quantization grid via bit-planes and scalar coefficients.<n>BPDQ enables serving Qwen2.5-72B on a single GTX 3090 with 83.85% GSM8K accuracy (vs. 90.83% at 16-bit)
  arXiv  Detail & Related papers  (2026-02-04T02:54:37Z)
• MergeQuant: Accurate 4-bit Static Quantization of Large Language Models by Channel-wise Calibration [23.752021919501207]
  We propose MergeQuant, an accurate and efficient per-channel static quantization framework.<n> MergeQuant integrates the per-channel quantization steps with the corresponding scalings and linear mappings through a Quantization Step Migration (QSM) method.<n>On Llama-2-7B model, MergeQuant achieves up to 1.77x speedup in decoding, and up to 2.06x speedup in end-to-end compared to FP16 baseline.
  arXiv  Detail & Related papers  (2025-03-07T04:52:28Z)
• TesseraQ: Ultra Low-Bit LLM Post-Training Quantization with Block Reconstruction [20.903193906931687]
  Post-training quantization (PTQ) is becoming the de facto method to reduce the memory footprint and improve the inference throughput of large language models (LLMs) We propose TesseraQ, a new state-of-the-art PTQ technique, to quantize the weights of LLMs to ultra-low bits. We demonstrate that TesseraQ can be seamlessly integrated with existing scaling or clipping-based PTQ algorithms.
  arXiv  Detail & Related papers  (2024-10-24T19:06:51Z)
• PTQ4DiT: Post-training Quantization for Diffusion Transformers [52.902071948957186]
  Post-training Quantization (PTQ) has emerged as a fast and data-efficient solution that can significantly reduce computation and memory footprint. We propose PTQ4DiT, a specifically designed PTQ method for DiTs. We demonstrate that our PTQ4DiT successfully quantizes DiTs to 8-bit precision while preserving comparable generation ability.
  arXiv  Detail & Related papers  (2024-05-25T02:02:08Z)
• AffineQuant: Affine Transformation Quantization for Large Language Models [58.45460102764]
  Post-Training Quantization (PTQ) has emerged as a subject of considerable interest due to its compression efficiency and cost-effectiveness in the context of training. Existing PTQ methods for Large-scale Language Models (LLMs) limit the optimization scope to scaling transformations between pre- and post-quantization weights. In this paper, we advocate for the direct optimization using equivalent Affine transformations in PTQ (AffineQuant)
  arXiv  Detail & Related papers  (2024-03-19T08:40:21Z)
• CBQ: Cross-Block Quantization for Large Language Models [66.82132832702895]
  Post-training quantization (PTQ) has played a key role in compressing large language models (LLMs) with ultra-low costs.<n>We propose CBQ, a cross-block reconstruction-based PTQ method for LLMs.<n> CBQ employs a cross-block dependency using a reconstruction scheme, establishing long-range dependencies across multiple blocks to minimize error accumulation.
  arXiv  Detail & Related papers  (2023-12-13T07:56:27Z)
• LLM-FP4: 4-Bit Floating-Point Quantized Transformers [38.23587031169402]
  We propose LLM-FP4 for quantizing both weights and activations in large language models (LLMs) down to 4-bit floating-point values. Compared to integer quantization, floating-point (FP) quantization is more flexible and can better handle long-tail or bell-shaped distributions. Our method, for the first time, can quantize both weights and activations in the LLaMA-13B to only 4-bit and achieves an average score of 63.1.
  arXiv  Detail & Related papers  (2023-10-25T17:59:32Z)
• Distribution-Flexible Subset Quantization for Post-Quantizing Super-Resolution Networks [68.83451203841624]
  This paper introduces Distribution-Flexible Subset Quantization (DFSQ), a post-training quantization method for super-resolution networks. DFSQ conducts channel-wise normalization of the activations and applies distribution-flexible subset quantization (SQ) It achieves comparable performance to full-precision counterparts on 6- and 8-bit quantization, and incurs only a 0.1 dB PSNR drop on 4-bit quantization.
  arXiv  Detail & Related papers  (2023-05-10T04:19:11Z)
• RPTQ: Reorder-based Post-training Quantization for Large Language Models [46.03754730678076]
  Large-scale language models (LLMs) have demonstrated impressive performance, but their deployment presents challenges due to their significant memory usage. We introduce a quantization method called RPTQ, which utilizes a reorder-based approach. In our experiments, RPTQ achieved a significant breakthrough by utilizing 3-bit activation in LLMs for the first time, resulting in a substantial reduction in memory usage.
  arXiv  Detail & Related papers  (2023-04-03T15:46:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.