Fine-tuning updates frequently stale activation monitors for language model safety while quantization does not, with degradation predictable and repairable via label-free realignment.
super hub Mixed citations
GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
Mixed citation behavior. Most common role is background (68%).
219
Pith papers citing it
Background
68% of classified citations
abstract
Generative Pre-trained Transformer models, known as GPT or OPT, set themselves apart through breakthrough performance across complex language modelling tasks, but also by their extremely high computational and storage costs. Specifically, due to their massive size, even inference for large, highly-accurate GPT models may require multiple performant GPUs, which limits the usability of such models. While there is emerging work on relieving this pressure via model compression, the applicability and performance of existing compression techniques is limited by the scale and complexity of GPT models. In this paper, we address this challenge, and propose GPTQ, a new one-shot weight quantization method based on approximate second-order information, that is both highly-accurate and highly-efficient. Specifically, GPTQ can quantize GPT models with 175 billion parameters in approximately four GPU hours, reducing the bitwidth down to 3 or 4 bits per weight, with negligible accuracy degradation relative to the uncompressed baseline. Our method more than doubles the compression gains relative to previously-proposed one-shot quantization methods, preserving accuracy, allowing us for the first time to execute an 175 billion-parameter model inside a single GPU for generative inference. Moreover, we also show that our method can still provide reasonable accuracy in the extreme quantization regime, in which weights are quantized to 2-bit or even ternary quantization levels. We show experimentally that these improvements can be leveraged for end-to-end inference speedups over FP16, of around 3.25x when using high-end GPUs (NVIDIA A100) and 4.5x when using more cost-effective ones (NVIDIA A6000). The implementation is available at https://github.com/IST-DASLab/gptq.
hub tools
citation-role summary
background 20
baseline 3
method 3
dataset 1
other 1
citation-polarity summary
claims ledger
- abstract Generative Pre-trained Transformer models, known as GPT or OPT, set themselves apart through breakthrough performance across complex language modelling tasks, but also by their extremely high computational and storage costs. Specifically, due to their massive size, even inference for large, highly-accurate GPT models may require multiple performant GPUs, which limits the usability of such models. While there is emerging work on relieving this pressure via model compression, the applicability and performance of existing compression techniques is limited by the scale and complexity of GPT models
authors
co-cited works
representative citing papers
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 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.
HodgeCover isolates the harmonic kernel of a simplicial Laplacian on an expert 2-complex to identify irreducible merge cycles and selects experts for aggressive compression, matching or exceeding baselines on open-weight MoE models.
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.
Lynx partitions KV cache bits into anchor and residual streams for progressive transfer, enabling speculative decoding on partial data followed by verification to match BF16 accuracy at 4-bit-like TTFT.
Mix-QVLA is a task-evidence-aware mixed-precision PTQ framework for VLA models that preserves task-relevant evidence via evidence-mass and attribution-distribution metrics to guide bit allocation under memory and BitOps constraints.
APEX4 co-designs pure INT4 GEMM kernels with ρ-aware granularity adaptation to deliver up to 2.09× end-to-end speedup on GPUs with low ρ while keeping LLaMA-2-70B perplexity within 0.63 of FP16.
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 retention from 40-50% to 58.8%.
SubFit enables better LLM compression by fitting residual bypasses to non-contiguously selected submodules, outperforming layer-granularity baselines in accuracy-perplexity trade-offs at 12.5-37.5% sparsity.
A new fault-injection framework enables a systematic empirical study that produces 17 takeaways on error propagation in LLM inference and four software-only mitigation directions.
Omega-QVLA is a post-training quantization framework achieving uniform W4A4 for VLA models' LLM backbone and DiT action head via composite SVD-Hadamard rotation and per-step scaling, matching FP16 success rates on LIBERO.
AIGaitor is the first claimed end-to-end on-device monocular motion-capture and deep-learning gait analysis pipeline demonstrated on consumer smartphones.
LlamaWeb is a WebGPU backend for llama.cpp that uses static memory planning, tunable kernels, and templated multi-precision support to cut memory use by 29-33% and raise decode throughput by 45-69% versus prior browser frameworks on tested hardware.
LongLive-2.0 delivers an NVFP4 parallel infrastructure that enables direct training of long multi-shot autoregressive diffusion video models and achieves up to 2.15x training and 1.84x inference speedups on Blackwell and other GPUs.
CFQ trains quantizer parameters and mixed-precision allocation to preserve counterfactual recourse validity, cost, and direction on Adult, German Credit, and COMPAS while matching accuracy of standard quantizers.
The paper introduces an outlier-injection attack that induces targeted weight collapse in LLMs under advanced quantization schemes including AWQ, GPTQ, and GGUF I-quants.
New metrics KSS and KPS are introduced to evaluate multilingual machine unlearning quality and cross-language consistency in LLMs, addressing limitations of single-language evaluation protocols.
MSD eliminates dequantization from the GEMM path by decomposing BF16 activations into multiple low-precision parts that multiply directly with INT8 or MXFP4 weights, achieving near-16 effective bits for INT8 and 6.6 for MXFP4 with reduced HBM traffic.
LoopQ provides a loop-aware PTQ framework for recursive Transformers that mitigates distribution shift, state reuse, and recursive error accumulation, yielding 68.8% higher average accuracy and 87.7% lower perplexity under W4A4 versus static baselines.
Diffusion language models develop early-layer collapse around an indispensable super-outlier due to overtraining, resulting in higher compressibility and reversed optimal sparsity patterns versus autoregressive models.
A single fused int4 KV cache kernel on Apple Silicon outperforms fp16 in latency with 3x memory compression and near-zero quality loss on tested models.
Dynamic quantization creates side channels allowing partial or full recovery of other users' batched data in at least four popular ML frameworks.
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 perplexity cost.
citing papers explorer
-
Do Activation Monitors Survive Model Updates? Benchmarking, Predicting, and Repairing Activation-Monitor Staleness
Fine-tuning updates frequently stale activation monitors for language model safety while quantization does not, with degradation predictable and repairable via label-free realignment.
-
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.
-
HodgeCover: Higher-Order Topological Coverage Drives Compression of Sparse Mixture-of-Experts
HodgeCover isolates the harmonic kernel of a simplicial Laplacian on an expert 2-complex to identify irreducible merge cycles and selects experts for aggressive compression, matching or exceeding baselines on open-weight MoE models.
-
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.
-
Lynx: Progressive Speculative Quantization for accelerating KV Transfer in Long-Context Inference
Lynx partitions KV cache bits into anchor and residual streams for progressive transfer, enabling speculative decoding on partial data followed by verification to match BF16 accuracy at 4-bit-like TTFT.
-
Mix-QVLA: Task-Evidence-Aware Mixed-Precision Quantization of Vision-Language-Action Models
Mix-QVLA is a task-evidence-aware mixed-precision PTQ framework for VLA models that preserves task-relevant evidence via evidence-mass and attribution-distribution metrics to guide bit allocation under memory and BitOps constraints.
-
APEX4: Efficient Pure W4A4 LLM Inference via Intra-SM Compute Rebalancing
APEX4 co-designs pure INT4 GEMM kernels with ρ-aware granularity adaptation to deliver up to 2.09× end-to-end speedup on GPUs with low ρ while keeping LLaMA-2-70B perplexity within 0.63 of FP16.
-
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 retention from 40-50% to 58.8%.
-
From Layers to Submodules: Rethinking Granularity in Replacement-Based LLM Compression
SubFit enables better LLM compression by fitting residual bypasses to non-contiguously selected submodules, outperforming layer-granularity baselines in accuracy-perplexity trade-offs at 12.5-37.5% sparsity.
-
Not All Errors Are Equal: A Systematic Study of Error Propagation in Large Language Model Inference
A new fault-injection framework enables a systematic empirical study that produces 17 takeaways on error propagation in LLM inference and four software-only mitigation directions.
-
{\Omega}-QVLA: Robust Quantization for Vision-Language-Action Models via Composite Rotation and Per-step Scaling
Omega-QVLA is a post-training quantization framework achieving uniform W4A4 for VLA models' LLM backbone and DiT action head via composite SVD-Hadamard rotation and per-step scaling, matching FP16 success rates on LIBERO.
-
AIGaitor: Privacy-preserving and cloud-free motion analysis for everyone, using edge computing
AIGaitor is the first claimed end-to-end on-device monocular motion-capture and deep-learning gait analysis pipeline demonstrated on consumer smartphones.
-
Llamas on the Web: Memory-Efficient, Performance-Portable, and Multi-Precision LLM Inference with WebGPU
LlamaWeb is a WebGPU backend for llama.cpp that uses static memory planning, tunable kernels, and templated multi-precision support to cut memory use by 29-33% and raise decode throughput by 45-69% versus prior browser frameworks on tested hardware.
-
LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation
LongLive-2.0 delivers an NVFP4 parallel infrastructure that enables direct training of long multi-shot autoregressive diffusion video models and achieves up to 2.15x training and 1.84x inference speedups on Blackwell and other GPUs.
-
When Bits Break Recourse: Counterfactual-Faithful Quantization
CFQ trains quantizer parameters and mixed-precision allocation to preserve counterfactual recourse validity, cost, and direction on Adult, German Credit, and COMPAS while matching accuracy of standard quantizers.
-
Widening the Gap: Exploiting LLM Quantization via Outlier Injection
The paper introduces an outlier-injection attack that induces targeted weight collapse in LLMs under advanced quantization schemes including AWQ, GPTQ, and GGUF I-quants.
-
Knowledge Beyond Language: Bridging the Gap in Multilingual Machine Unlearning Evaluation
New metrics KSS and KPS are introduced to evaluate multilingual machine unlearning quality and cross-language consistency in LLMs, addressing limitations of single-language evaluation protocols.
-
Multi-Scale Dequant: Eliminating Dequantization Bottleneck via Activation Decomposition for Efficient LLM Inference
MSD eliminates dequantization from the GEMM path by decomposing BF16 activations into multiple low-precision parts that multiply directly with INT8 or MXFP4 weights, achieving near-16 effective bits for INT8 and 6.6 for MXFP4 with reduced HBM traffic.
-
LoopQ: Quantization for Recursive Transformers
LoopQ provides a loop-aware PTQ framework for recursive Transformers that mitigates distribution shift, state reuse, and recursive error accumulation, yielding 68.8% higher average accuracy and 87.7% lower perplexity under W4A4 versus static baselines.
-
Layer Collapse in Diffusion Language Models
Diffusion language models develop early-layer collapse around an indispensable super-outlier due to overtraining, resulting in higher compressibility and reversed optimal sparsity patterns versus autoregressive models.
-
When Quantization Is Free: An int4 KV Cache That Outruns fp16 on Apple Silicon
A single fused int4 KV cache kernel on Apple Silicon outperforms fp16 in latency with 3x memory compression and near-zero quality loss on tested models.
-
Quantamination: Dynamic Quantization Leaks Your Data Across the Batch
Dynamic quantization creates side channels allowing partial or full recovery of other users' batched data in at least four popular ML frameworks.
-
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 perplexity cost.
-
When W4A4 Breaks Camouflaged Object Detection: Token-Group Dual-Constraint Activation Quantization
COD-TDQ uses token-group scaling and dual-constraint projection to fix 4-bit activation quantization for camouflaged object detection, delivering more than 0.12 higher Sα scores than prior methods on four benchmarks without retraining.
-
When Flat Minima Fail: Characterizing INT4 Quantization Collapse After FP32 Convergence
FP32-converged language models enter a post-convergence phase where INT4 quantization error explodes while FP32 perplexity remains stable, with onset tied to fine convergence rather than learning rate decay.
-
Hidden Reliability Risks in Large Language Models: Systematic Identification of Precision-Induced Output Disagreements
PrecisionDiff is a differential testing framework that uncovers widespread precision-induced behavioral disagreements in aligned LLMs, including safety-critical jailbreak divergences across precision formats.
-
ENEC: A Lossless AI Model Compression Method Enabling Fast Inference on Ascend NPUs
ENEC delivers 3.43X higher throughput than DietGPU and 1.12X better compression ratio than nvCOMP for lossless model weight compression on Ascend NPUs, yielding up to 6.3X end-to-end inference speedup.
-
Why Smaller Is Slower? Dimensional Misalignment in Compressed LLMs
Dimensional misalignment slows compressed LLMs on GPUs; GAC uses knapsack optimization to achieve full alignment and up to 1.5x speedup on Llama-3-8B while preserving quality.
-
QuantVLA: Scale-Calibrated Post-Training Quantization for Vision-Language-Action Models
QuantVLA is the first post-training quantization framework for VLA models that quantizes the diffusion transformer action head and reports higher task success rates than full-precision baselines with roughly 70% memory savings on the quantized components.
-
CORP: Closed-Form One-shot Representation-Preserving Structured Pruning for Transformers
CORP performs one-shot structured pruning of Transformers by modeling removed components as affine functions of retained ones and solving closed-form ridge regressions on calibration data to fold compensation into weights, retaining 83.27% Top-1 accuracy on DeiT-Huge after 50% pruning.
-
Vec-LUT: Vector Table Lookup for Parallel Ultra-Low-Bit LLM Inference on Edge Devices
Vec-LUT delivers up to 4.2x speedup over prior LUT methods for parallel ultra-low-bit LLM inference on edge devices by unifying lookups across tokens and adding cache-aware tensor layouts.
-
Four Over Six: More Accurate NVFP4 Quantization with Adaptive Block Scaling
Four Over Six adaptively scales blocks in NVFP4 quantization to smaller FP4 values, making representable value distributions more uniform and reducing quantization error especially for near-maximal values.
-
Decomposed Trust: Privacy, Adversarial Robustness, Ethics, and Fairness in Low-Rank LLMs
Low-rank compression preserves training-data privacy and improves adversarial robustness but weakens personal-information protection, reduces ethical behavior in zero-shot use, and harms fairness.
-
SpinQuant: LLM quantization with learned rotations
SpinQuant learns optimal rotations to enable accurate 4-bit quantization of LLM weights, activations, and KV cache, reducing the zero-shot gap to full precision to 2.9 points on LLaMA-2 7B.
-
Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads
Medusa augments LLMs with multiple decoding heads and tree-based attention to predict and verify several tokens in parallel, yielding 2.2-3.6x inference speedup via two fine-tuning regimes.
-
QLoRA: Efficient Finetuning of Quantized LLMs
QLoRA finetunes 4-bit quantized LLMs via LoRA adapters to match full-precision performance while using far less memory, enabling 65B-scale training on single GPUs and producing Guanaco models near ChatGPT level.
-
SAB-LVLM: Significance-Aware Binarization for Large Vision-Language Models
SAB-LVLM proposes a significance-aware binarization technique for LVLMs that uses modality-guided Hessian-based maps to reweight binarization errors and improve performance under 1-bit constraints.
-
MxGLUT: A Reconfigurable LUT-Centric Broadcast Dataflow Accelerator for Mixed-Precision GEMM
MxGLUT introduces a reconfigurable LUT-centric broadcast dataflow accelerator with mixed-precision LUT-based PEs that unifies FP8-INT4 and FP8-FP8 GEMM without separate FP datapaths, reporting up to 2.16x prefill speedup and 0.492 TFLOPS/mm² area efficiency in 28nm synthesis.
-
OmniPilot: An Uncertainty-Aware LLM Inference Advisor for Heterogeneous GPU Clusters
OmniPilot combines conformal quantile regression with OOD detection to rank LLM serving configurations on mixed GPUs, reporting 6.2% MAPE throughput prediction and 95% top-1 accuracy on 460 benchmark runs while abstaining on unsupported cases.
-
When AI Reviews Its Own Code: Recursive Self-Training Collapse in Code LLMs
Experiments across code LLMs show no-review collapses fastest, human-gated filters slow collapse, and AI self-gates lose effect over time, degenerating to ungated self-training under self-confirming acceptance as proven via gated distributional reweighting and spectral analysis.
-
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.
-
DynamicPTQ: Mitigating Activation Quantization Collapse via Residual-Stream Dynamics
DynamicPTQ uses new metrics of residual-stream dynamics to apply 8-bit activation precision only to quantization-sensitive layers in W4A4KV4 LLM inference, improving perplexity and QA performance over static smoothing baselines.
-
LC-QAT: Data-Efficient 2-Bit QAT for LLMs via Linear-Constrained Vector Quantization
LC-QAT achieves data-efficient 2-bit weight-only QAT for LLMs by representing quantized weights as a learned affine transform over discrete vectors, supporting end-to-end optimization from a high-quality PTQ start.
-
Quality Is Not a Safety Proxy Under Quantization
Across 51 quantized checkpoints, quality metrics fail to predict safety drops in 36 pairings and 10 hidden-danger cases, while a new RTSI screen routes all 10 dangerous rows to testing at matched bucket size.
-
SPEAR: A System for Post-Quantization Error-Adaptive Recovery Enabling Efficient Low-Bit LLM Serving
SPEAR places input-dependent error compensators at CKA-selected layers and fuses them into low-bit GEMMs to recover 56-75% of the W4-to-FP16 perplexity gap with <1% memory overhead and near-baseline latency.
-
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.
-
FAIR-Calib: Frontier-Aware Instability-Reweighted Calibration for Post-Training Quantization of Diffusion Large Language Models
FAIR-Calib is a frontier-aware instability-reweighted calibration framework for PTQ of dLLMs that minimizes reweighted hidden-state MSE to reduce frontier decision flips.
-
AlphaQ: Calibration-Free Bit Allocation for Mixture-of-Experts Quantization
AlphaQ performs calibration-free mixed-precision quantization of MoE models by allocating higher bits to experts whose weight spectra exhibit stronger heavy-tailed structure according to HT-SR theory, outperforming calibration-based methods and reaching near full-precision accuracy at 3.5 average bi
-
STaR-Quant: State-Time Consistent Post-Training Quantization for Diffusion Large Language Models
STaR-Quant provides a state-time consistent PTQ framework for DLLMs using SGAT and TAC to improve low-bit weight-activation quantization.