REVIEW 25 cited by
FlatQuant: Flatness Matters for LLM Quantization
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
FlatQuant: Flatness Matters for LLM Quantization
read the original abstract
Recently, quantization has been widely used for the compression and acceleration of large language models (LLMs). Due to the outliers in LLMs, it is crucial to flatten weights and activations to minimize quantization error with equally spaced quantization points. Prior research explores various pre-quantization transformations to suppress outliers, such as per-channel scaling and Hadamard transformation. However, we observe that these transformed weights and activations can still exhibit steep and dispersed distributions. In this paper, we propose FlatQuant (Fast and Learnable Affine Transformation), a new post-training quantization approach that enhances the flatness of weights and activations. Our approach identifies optimal affine transformations for each linear layer, calibrated in hours via a lightweight objective. To reduce runtime overhead of affine transformation, we apply Kronecker product with two lightweight matrices, and fuse all operations in FlatQuant into a single kernel. Extensive experiments demonstrate that FlatQuant establishes a new state-of-the-art benchmark for quantization. For example, it achieves less than 1\% accuracy drop for W4A4 quantization on the LLaMA-3-70B model, surpassing SpinQuant by 7.5\%. Additionally, it provides up to 2.3x prefill speedup and 1.7x decoding speedup compared to the FP16 model. Code is available at: https://github.com/ruikangliu/FlatQuant.
Forward citations
Cited by 25 Pith papers
-
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.
-
{\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.
-
Rotation-Aligned Key Channel Pruning for Efficient Vision-Language Model Inference
RotateK uses online PCA-based rotation to align token-dependent key channel importance into a shared subspace, enabling accurate head-wise structured pruning and faster decoding in VLMs compared to prior token or chan...
-
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% memor...
-
KronQ: LLM Quantization via Kronecker-Factored Hessian
Kronecker-factored Hessian PTQ with bidirectional incoherence and joint-trace mixed precision yields stable 2-bit LLM weights where activation-only methods fail.
-
HEPTv2: End-to-End Efficient Point Transformer for Charged Particle Reconstruction
HEPTv2 achieves 98.6% double-majority tracking efficiency at 0.8% fake rate with ~15 ms inference and 0.4 GB memory on TrackML using an end-to-end point transformer with locality-sensitive hashing.
-
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...
-
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.
-
LiftQuant: Continuous Bit-Width LLM via Dimensional Lifting and Projection
LiftQuant uses dimensional lifting of weights to a higher-dimensional 1-bit lattice followed by projection to achieve tunable continuous bit-widths in LLM quantization while remaining hardware-friendly.
-
LiftQuant: Continuous Bit-Width LLM via Dimensional Lifting and Projection
LiftQuant enables continuous bit-width LLM quantization via dimensional lifting and projection from a 1-bit lattice, allowing 2.4-bit compression of 70B models that outperforms fixed 2-bit baselines on identical hardware.
-
Qift: Shift-Friendly No-Zero W2 Post-Training Quantization for Rotated W2A4/KV4 LLM Inference
Qift defines a fixed no-zero W2 level set for rotated weights that improves W2A4 perplexity and accuracy on LLaMA-2-7B and LLaMA-3.1-8B over the standard {-2,-1,0,1} set.
-
Quantized Reasoning Models Think They Need to Think Longer, but They Do Not
Post-training quantization increases overthinking errors in reasoning models; a logit penalty on curated overthinking markers reduces CoT length 12-23% without accuracy loss.
-
InfoQuant: Shaping Activation Distributions for Low-Bit LLM Quantization
InfoQuant applies information-theoretic analysis to design quantization-friendly activation distributions via PSOT and adaptive outlier selection, preserving 97% of FP accuracy on average under W4A4KV4 across LLMs.
-
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.
-
Theory-optimal Quantization Based on Flatness
The paper introduces the Flatness metric, derives a theory-optimal quantization solution, and presents BDQ that uses bidirectional diagonal transformations to reduce outlier impact, achieving under 1% drop at W4A4 on ...
-
QuantClaw: Precision Where It Matters for OpenClaw
QuantClaw dynamically routes precision in agent workflows to cut cost by up to 21.4% and latency by 15.7% while keeping or improving task performance.
-
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...
-
RUQuant: Towards Refining Uniform Quantization for Large Language Models
RUQuant uses block-wise composite orthogonal matrices from Householder reflections and Givens rotations plus a fine-tuned global reflection to achieve 99.8% full-precision accuracy at W6A6 and 97% at W4A4 for 13B LLMs...
-
BTC-LLM: Efficient Sub-1-Bit LLM Quantization via Learnable Transformation and Binary Codebook
BTC-LLM uses a binary codebook for pattern clustering and a learnable transformation to achieve 0.7-1.11 bit LLM quantization while limiting accuracy loss to a few percent on LLaMA and Qwen models.
-
MixFP4: Enhancing NVFP4 with Adaptive FP4/INT4 Block Representations
MixFP4 extends NVFP4 by adaptively selecting between two FP4 micro-formats per block using repurposed scale sign bits and a unified E2M2 compute path, claiming better accuracy than standard NVFP4 at 3.1% area and 1.5%...
-
GAMMA: Global Bit Allocation for Mixed-Precision Models under Arbitrary Budgets
GAMMA is a post-training framework that learns stable module sensitivity rankings for mixed-precision LLM quantization and projects them to exact bit budgets via integer programming, enabling reuse across arbitrary me...
-
TACO: Efficient Communication Compression of Intermediate Tensors for Scalable Tensor-Parallel LLM Training
TACO compresses tensor-parallel intermediate tensors with an adaptive FP8 scheme and fused kernels, yielding up to 1.87X throughput gains on GPT and Qwen models with near-lossless accuracy.
-
OSC: Hardware Efficient W4A4 Quantization via Outlier Separation in Channel Dimension
OSC separates token-persistent outlier channels in activations into a compact high-precision tensor for dual-path 4-bit GEMM computation, limiting accuracy loss to roughly 1-2 points on Qwen3 models while delivering u...
-
Efficient Matrix Implementation for Rotary Position Embedding
RoME reformulates RoPE as matrix operations to eliminate dimension-specific vector overhead and enable fused execution on modern hardware while remaining mathematically equivalent.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.