SPEAR: A System for Post-Quantization Error-Adaptive Recovery Enabling Efficient Low-Bit LLM Serving

• URL: http://arxiv.org/abs/2606.11244v1
• Date: Thu, 04 Jun 2026 22:38:53 GMT
• Title: SPEAR: A System for Post-Quantization Error-Adaptive Recovery Enabling Efficient Low-Bit LLM Serving
• Abstract summary: We present SPEAR, a system for post-quantization error-adaptive recovery that improves low-bit LLM serving.<n> SPEAR introduces lightweight Error Compensators (ECs) by per-token gates and places them only at the most error-sensitive layers identified through a CKA-guided entropy-aware diagnostic.<n>We show that SPEAR recovers 56-75% of the perplexity gap between W4 and FP16 while adding less than 1% model memory overhead and maintaining latency comparable to a widely used 4-bit serving deployment.
• Score: 26.96887030437247
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Efficient large language model (LLM) serving is increasingly constrained by deployment cost. Quantization is a key technique for reducing serving cost, yet even state-of-the-art 4-bit quantizers exhibit a noticeable quality gap from FP16, particularly for smaller models where low-bit serving is most beneficial. We identify a fundamental cause of this gap: quantization error is highly input-dependent and varies substantially across tokens, while existing post-quantization compensation methods are static and apply identical corrections to all inputs. As a result, easy tokens are over-corrected while hard tokens remain under-corrected. We present SPEAR, a system for post-quantization error-adaptive recovery that improves low-bit LLM serving. SPEAR introduces lightweight Error Compensators (ECs) modulated by per-token gates and places them only at the most error-sensitive layers identified through a CKA-guided entropy-aware diagnostic. This focuses a small parameter budget where it is most effective. Efficient deployment of ECs presents several systems challenges, including additional computation, tensor-parallel synchronization caused by input-dependent gating, and latency instability across configurations. SPEAR addresses these issues through adaptive kernel-fusion dispatch, combining an epilogue-integrated peer-reduction kernel with P2P dual-write to fuse the post-EC computation into low-bit GEMMs, and an SLO-constrained EC-aware scheduler for predictable serving performance. Across challenging per-channel quantization settings, SPEAR recovers 56-75% of the perplexity gap between W4 and FP16 while adding less than 1% model memory overhead and maintaining latency comparable to a widely used 4-bit serving deployment.

Related papers

• ReSET: Accurate Latency-Critical NVFP4 Reasoning via Step-Aware Temperature Scaling [9.642832832617144]
  We analyze the effect of NVFP4 quantization on token-level uncertainty during reasoning.<n>We show that quantization increases incorrect sampling at low-entropy symbolic tokens.<n>We further design a core-$M$FP4 kernel for latency-critical decoding using both token-level and step-level entropy signals.
  arXiv  Detail & Related papers  (2026-06-11T11:47:40Z)
• Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs [78.01752802974855]
  We propose Mix-Quant, a simple and effective phase-aware quantization framework for fast agentic inference.<n>We show that Mix-Quant preserves task performance while delivering significant efficiency improvements, achieving up to a 3x speedup during prefilling.
  arXiv  Detail & Related papers  (2026-05-19T17:50:17Z)
• SOAR: Scale Optimization for Accurate Reconstruction in NVFP4 Quantization [19.022444007775896]
  NVFP4 has recently emerged as an efficient 4-bit microscaling format for large language models.<n>Existing methods often yield suboptimal performance due to inflexible scale selection and the coupled treatment of quantization and dequantization scales.<n>We propose Scale Optimization for Accurate Reconstruction (SOAR), a novel post-training quantization framework that improves the accuracy of NVFP4 quantization.
  arXiv  Detail & Related papers  (2026-05-12T15:13:18Z)
• SERQ: Saliency-Aware Low-Rank Error Reconstruction for LLM Quantization [7.372706701787234]
  Post-training quantization (PTQ) has emerged as a prevailing technique for deploying large language models efficiently.<n>We propose SERQ, a saliency-aware error reconstruction method for low-bit LLM inference that employs a single low-rank compensation matrix.
  arXiv  Detail & Related papers  (2026-03-09T10:04:12Z)
• QTALE: Quantization-Robust Token-Adaptive Layer Execution for LLMs [0.0]
  Large language models (LLMs) demand substantial computational and memory resources.<n>We propose QTALE, a novel framework that enables seamless integration of token-adaptive execution with quantization.
  arXiv  Detail & Related papers  (2026-02-11T02:19:11Z)
• AMS-QUANT: Adaptive Mantissa Sharing for Floating-point Quantization [7.413057271242686]
  Quantization, particularly floating-point quantization, is known to be capable of speeding up large language models (LLMs) inference.<n>We propose AMS-Quant, which explores floating-point quantization exploration from integer bitwidths to non-integer bit-widths.<n>We show that AMS-Quant can quantize the model to FP-5.33-e2m3 and FP4.25-e2m2, and significantly speed up the decoding over FP16 inference.
  arXiv  Detail & Related papers  (2025-10-16T15:37:23Z)
• PT$^2$-LLM: Post-Training Ternarization for Large Language Models [52.4629647715623]
  Large Language Models (LLMs) have shown impressive capabilities across diverse tasks, but their large memory and compute demands hinder deployment.<n>We propose PT$2$-LLM, a post-training ternarization framework tailored for LLMs.<n>At its core is an Asymmetric Ternary Quantizer equipped with a two-stage refinement pipeline.
  arXiv  Detail & Related papers  (2025-09-27T03:01:48Z)
• Joint Transmit and Pinching Beamforming for Pinching Antenna Systems (PASS): Optimization-Based or Learning-Based? [89.05848771674773]
  A novel antenna system ()-enabled downlink multi-user multiple-input single-output (MISO) framework is proposed.<n>It consists of multiple waveguides, which equip numerous low-cost antennas, named (PAs)<n>The positions of PAs can be reconfigured to both spanning large-scale path and space.
  arXiv  Detail & Related papers  (2025-02-12T18:54:10Z)
• Optimizing Large Language Model Training Using FP4 Quantization [73.55459961002371]
  Quantized training presents a promising solution by enabling low-bit arithmetic operations to reduce costs.<n>This work introduces the first FP4 training framework for large language models (LLMs)
  arXiv  Detail & Related papers  (2025-01-28T18:04:50Z)
• EoRA: Fine-tuning-free Compensation for Compressed LLM with Eigenspace Low-Rank Approximation [84.70637613266835]
  EoRA is a fine-tuning-free method that augments compressed Large Language Models with low-rank matrices.<n>EoRA consistently outperforms prior training-free low rank methods in recovering the accuracy of compressed LLMs.
  arXiv  Detail & Related papers  (2024-10-28T17:59:03Z)
• Fast Flux-Activated Leakage Reduction for Superconducting Quantum Circuits [84.60542868688235]
  leakage out of the computational subspace arising from the multi-level structure of qubit implementations. We present a resource-efficient universal leakage reduction unit for superconducting qubits using parametric flux modulation. We demonstrate that using the leakage reduction unit in repeated weight-two stabilizer measurements reduces the total number of detected errors in a scalable fashion.
  arXiv  Detail & Related papers  (2023-09-13T16:21:32Z)
• PAMS: Quantized Super-Resolution via Parameterized Max Scale [84.55675222525608]
  Deep convolutional neural networks (DCNNs) have shown dominant performance in the task of super-resolution (SR) We propose a new quantization scheme termed PArameterized Max Scale (PAMS), which applies the trainable truncated parameter to explore the upper bound of the quantization range adaptively. Experiments demonstrate that the proposed PAMS scheme can well compress and accelerate the existing SR models such as EDSR and RDN.
  arXiv  Detail & Related papers  (2020-11-09T06:16:05Z)

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.