REVIEW 33 cited by
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression
read the original abstract
Recent advances in large language model (LLM) pretraining have led to high-quality LLMs with impressive abilities. By compressing such LLMs via quantization to 3-4 bits per parameter, they can fit into memory-limited devices such as laptops and mobile phones, enabling personalized use. However, quantization down to 3-4 bits per parameter usually leads to moderate-to-high accuracy losses, especially for smaller models in the 1-10B parameter range, which are well-suited for edge deployments. To address this accuracy issue, we introduce the Sparse-Quantized Representation (SpQR), a new compressed format and quantization technique which enables for the first time near-lossless compression of LLMs across model scales, while reaching similar compression levels to previous methods. SpQR works by identifying and isolating outlier weights, which cause particularly-large quantization errors, and storing them in higher precision, while compressing all other weights to 3-4 bits, and achieves relative accuracy losses of less than 1% in perplexity for highly-accurate LLaMA and Falcon LLMs. This makes it possible to run 33B parameter LLM on a single 24 GB consumer GPU without any performance degradation at 15% speedup thus making powerful LLMs available to consumer without any downsides. SpQR comes with efficient algorithms for both encoding weights into its format, as well as decoding them efficiently at runtime. Specifically, we provide an efficient GPU inference algorithm for SpQR which yields faster inference than 16-bit baselines at similar accuracy, while enabling memory compression gains of more than 4x.
Forward citations
Cited by 33 Pith papers
-
Alignment Collapse Under KV Cache Quantization: Diagnosis and Mitigation
KV cache quantization silently erodes LLM safety alignment via vulnerable low-dimensional subspaces, diagnosed by Per-Channel Reduction into three failure modes and mitigated training-free with up to 97% recovery.
-
GPTQ-intrinsic LoRA: A Near-optimal Algorithm for Low-precision Quantization with Low-rank Adaptation
GPTQ-intrinsic LoRA augments GPTQ with intrinsic low-rank compensation via Hessian modification to achieve layer-wise reconstruction bounds that match information-theoretic lower bounds under structural assumptions.
-
OrbitQuant: Data-Agnostic Quantization for Image and Video Diffusion Transformers
OrbitQuant is a data-agnostic PTQ technique for DiTs that uses RPBH rotation in a normalized basis to enable a single codebook across all inputs, achieving SOTA low-bit performance on FLUX.1, CogVideoX and similar models.
-
Calibration Data Trade-offs Across Capability Dimensions: Why Multi-Source Mixing Matters for High-Sparsity LLM Pruning
Analysis of 15 calibration sources shows opposite-sign Spearman correlations between perplexity and retention across General vs. Math/Code dimensions in LLM pruning, and multi-source mixing via IGSP raises total reten...
-
Quantizing With Randomized Hadamard Transforms: Efficient Heuristic Now Proven
Two randomized Hadamard transforms suffice to make coordinate marginals O(d^{-1/2})-close to Gaussian for most quantization methods, with three needed for vector quantization to match uniform random rotations asymptotically.
-
Coverage-Based Calibration for Post-Training Quantization via Weighted Set Cover over Outlier Channels
COVERCAL selects PTQ calibration samples via weighted set cover over outlier channels, with a stylized clipping model showing missed coverage upper-bounds surrogate loss, yielding gains over random and other baselines...
-
Variance Is Not Importance: Structural Analysis of Transformer Compressibility Across Model Scales
High-variance activation directions are uncorrelated with predictions, transformer blocks grow more linear with depth, and single-block linear replacement yields 34x compression on Mistral's final block at a 1.71 perp...
-
HyperQuant: A Rate-Distortion-Optimal Quantization Pipeline for Large Language and Diffusion Models
HyperQuant unifies Hadamard transform, optimal lattice quantization, and entropy coding to outperform prior schemes on LLM weight and KV cache quantization down to 1.7 bits per scalar while preserving quality on a 19B...
-
TWLA: Achieving Ternary Weights and Low-Bit Activations for LLMs via Post-Training Quantization
TWLA is a PTQ method using E2M-ATQ, KOTMS, and ILA-AMP to enable W1.58A4 quantization for LLMs with maintained accuracy.
-
ReCache: Learning Budget-Aware Caching Schedules for Diffusion Models via REINFORCE
ReCache learns recomputation schedules via policy gradients to maximize quality under a target compute budget for any caching mechanism in diffusion models.
-
Do Transformers Need Three Projections? Systematic Study of QKV Variants
Q-K=V projection sharing in transformers matches standard QKV performance with 50% KV cache reduction and combines with GQA/MQA for up to 96.9% reduction across vision and language tasks.
-
GEMQ: Global Expert-Level Mixed-Precision Quantization for MoE LLMs
GEMQ applies global LP-based expert importance estimation and router fine-tuning within progressive quantization to cut memory and speed inference in MoE LLMs with little accuracy loss.
-
ActQuant: Sub-4-bit Action-Guided Quantization for Vision-Language-Action Models
ActQuant achieves sub-4-bit (down to 2.5 bpw) quantization of VLA models via action-contribution bit allocation and curvature-based scale tuning, retaining over 90% performance on LIBERO and physical robot tasks.
-
Breaking Modality Heterogeneity in Low-Bit Quantization for Large Vision-Language Models
SplitQ improves low-bit PTQ for VLMs by isolating modality-specific outlier channels via MOCD and applying dual-branch adaptive calibration via ACC, outperforming prior methods on six datasets across W4A8 to W3A2 settings.
-
XFP: Quality-Targeted Adaptive Codebook Quantization with Sparse Outlier Separation for LLM Inference
XFP introduces quality-targeted adaptive codebook quantization with sparse outlier separation that auto-selects parameters from cosine similarity floors, achieving high throughput and accuracy on Qwen3.5 models at low...
-
ADMM-Q: An Improved Hessian-based Weight Quantizer for Post-Training Quantization of Large Language Models
ADMM-Q is a new post-training quantization method using ADMM operator splitting that reduces WikiText-2 perplexity compared to GPTQ on Qwen3-8B across W3A16, W4A8, and W2A4KV4 settings.
-
XtraMAC: An Efficient MAC Architecture for Mixed-Precision LLM Inference on FPGA
XtraMAC unifies mixed-precision MAC on FPGA via shared integer mantissa products, delivering 1.4-2.0x higher compute density and up to 1.9x better energy efficiency.
-
WindowQuant: Mixed-Precision KV Cache Quantization based on Window-Level Similarity for VLMs Inference Optimization
WindowQuant performs window-adaptive mixed-precision KV cache quantization guided by similarity to the text prompt, with reordering to enable efficient inference in VLMs.
-
BitRL: Reinforcement Learning with 1-bit Quantized Language Models for Resource-Constrained Edge Deployment
BitRL enables on-device RL agents via 1-bit quantized language models, delivering 10-16x memory reduction and 3-5x energy efficiency gains with 85-98% retained performance.
-
From Signal Degradation to Computation Collapse: Uncovering the Two Failure Modes of LLM Quantization
LLM 2-bit quantization fails via either cumulative signal degradation or early computation collapse in key components.
-
LBLLM: Lightweight Binarization of Large Language Models via Three-Stage Distillation
LBLLM achieves better accuracy than prior binarization methods for LLMs by decoupling weight and activation quantization through initialization, layer-wise distillation, and learnable activation scaling.
-
GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling
GSQ applies a Gumbel-Softmax relaxation to learn discrete grid assignments in scalar quantization, closing most of the accuracy gap to vector methods like QTIP on Llama-3.1 models at 2-3 bits while using only symmetri...
-
GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling
GSQ uses Gumbel-Softmax to optimize scalar quantization grids for LLMs, closing most of the accuracy gap to vector methods like QTIP at 2-3 bits per parameter while using symmetric scalar grids compatible with existin...
-
FP4 Explore, BF16 Train: Diffusion Reinforcement Learning via Efficient Rollout Scaling
Sol-RL decouples FP4-based candidate exploration from BF16 policy optimization in diffusion RL, delivering up to 4.64x faster convergence with maintained or superior alignment performance on models like FLUX.1 and SD3.5.
-
MorphoQuant: Modality-Aware Quantization for Omni-modal Large Language Models
MorphoQuant proposes DABC and MDQFO for 4-bit quantization of omni-modal LLMs, claiming superior performance over SOTA W4A4 methods and even W4A16 baselines on benchmarks like ScienceQA.
-
TStore: Rethinking AI Model Hub with Tensor-Centric Compression
TStore reduces AI model storage via tensor-level fingerprinting, clustering, and compression without annotations while claiming to preserve usability.
-
From 2:4 to 8:16 sparsity patterns in LLMs for Outliers and Weights with Variance Correction
8:16 sparsity with variance correction and outlier handling lets compressed LLMs match or exceed dense-model accuracy under fixed memory limits, outperforming the common 2:4 pattern in flexibility.
-
EntroLLM: Entropy Encoded Weight Compression for Efficient Large Language Model Inference on Edge Devices
EntroLLM applies tensor-level mixed quantization to reduce weight entropy then uses Huffman coding for up to 65% storage savings and faster inference on memory-limited edge devices without retraining.
-
StatQAT: Statistical Quantizer Optimization for Deep Networks
A statistical error analysis framework yields iterative and analytic quantizers that improve accuracy and stability when incorporated into quantization-aware training for integer and floating-point formats.
-
TStore: Rethinking AI Model Hub with Tensor-Centric Compression
TensorHub reduces storage in AI model hubs via tensor-centric deduplication and compression while keeping model performance intact.
-
Improving Quantized Model Performance in Qualitative Analysis with Multi-Pass Prompt Verification
A multi-pass prompt verification method stabilizes and improves accuracy of 4-bit and lower quantized LLaMA-3.1 models for thematic extraction from interview data, though 8-bit versions remain closest to a human-plus-...
-
Network Edge Inference for Large Language Models: Principles, Techniques, and Opportunities
A survey synthesizing challenges, system architectures, model optimizations, deployment methods, and resource management techniques for large language model inference at the network edge.
-
A Survey on Efficient Inference for Large Language Models
The paper surveys techniques to speed up and reduce the resource needs of LLM inference, organized by data-level, model-level, and system-level changes, with comparative experiments on representative methods.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.