arXiv AI
Jun 9
High-Rate Quantized Matrix Multiplication II
arXiv:2605. 13768v2 Announce Type: replace-cross Abstract: This is the second part of the work investigating quantized matrix multiplication (MatMul).
Transforms for LLM Quantization: The Great Inversion and Format Co-Design
The paper surveys the use of linear, function‑preserving transforms in 4‑bit large‑language‑model (LLM) quantization, formalizing the underlying principle as the "Great Inversion"—the trade‑off between energy concentration favored by allocation‑flexible coding and within‑group flattening favored by grouped shared‑scale quantization. It reviews 200 works, classifies 43 transform methods by structure, data‑awareness, construction approach, and runtime cost, and examines how they interact with GPTQ rounding. The study also explores how different number formats (FP4, MXFP4, NVFP4) influence the optimal transform choice and outlines open research problems. "whyItMatters":"The survey clarifies the conflicting objectives in transform‑based LLM quantization and provides a practical guide for selecting transforms based on deployment regime, thereby informing future research and deployment strategies."
Related stories
arXiv Machine Learning
Jun 2
WUSH: Near-Optimal Adaptive Transforms for LLM Quantization
arXiv:2512. 00956v3 Announce Type: replace Abstract: Quantizing LLM weights and activations is a standard approach for efficient deployment, but a few extreme outliers can stretch the dynamic range and amplify low-bit quantization errors.
arXiv Computation and Language
Sep 11
Structured Transforms for Low-Overhead Quantization of Language Models
The paper revisits Kashin‑decomposition‑based weight quantization for large language models, introducing an improved algorithm that uses a sign‑randomized Discrete Cosine Transform (DCT) instead of a dense random orthogonal matrix. This change reduces per‑iteration cost from ≠(N^2) to ≠(N log N) and, combined with a greedy alternating‑update scheme, guarantees the four‑peak distribution needed for stable 2‑bit clustering while eliminating the need for multi‑restart k‑means. The resulting JAX pipeline, when paired with OPTQ‑style error compensation and QuIP‑style incoherence preprocessing, competes with state‑of‑the‑art quantization methods on OPT, Llama‑2, and Pythia at 4‑bit per channel, and remains numerically stable under stress configurations that cause other methods to diverge.
arXiv Machine Learning
Jul 24
KroQuant: Kronecker-Structured Block Transforms for Efficient Post-Training Quantization of Diffusion Transformers
arXiv:2607. 21446v1 Announce Type: new Abstract: Post-training quantization (PTQ) of diffusion transformers (DiTs) to W4A4 severely degrades output quality, because activations entering each linear layer contain outliers that 4-bit formats cannot represent.
arXiv Machine Learning
Jul 22
Contraction-Gauge Preconditioning for Quantized Matrix Multiplication
arXiv:2607. 18745v1 Announce Type: new Abstract: We study low-precision computation of C=AB with both factors quantized.
arXiv AI
Sep 4
HARP: Hadamard-Preconditioned Adaptive Rotation Processor for Extreme LLM Quantization
HARP (Hadamard‑Preconditioned Adaptive Rotation Processor) is a learnable, structured two‑sided orthogonal processor that replaces fixed randomized Hadamard transforms in post‑training quantization of large language models. By representing rotations as sparse butterfly‑like block‑orthogonal stages and supporting mixed‑radix schedules, HARP adapts the quantization basis to each layer and calibration distribution while maintaining full‑precision equivalence. Across 2–4‑bit settings on Llama models from 1B to 70B, HARP consistently improves perplexity, delivers the strongest zero‑shot gains at 2 bits, and preserves deployment efficiency—achieving 128 tokens per second on Llama 2 7B at 2 bits, roughly 90% of RHT throughput and over twice the speed of FP16.
arXiv Machine Learning
Sep 10
A Nuclear-Norm Lower Bound for Dithered Scalar Quantization of Matrix Products
arXiv:2609.05641v1 Announce Type: cross Abstract: We consider the problem of minimizing error in quantized matrix multiplication $C=AB$. Scalar quantization of the factors introduces rounding errors...
arXiv AI
Jul 13
Signed Symmetric Quantization for Few-Bit Integers
arXiv:2607. 08779v1 Announce Type: cross Abstract: The signed integer alphabet contains one more negative representable value than positive.
Hugging Face Trending Papers
Oct 5
StagQ: Constraint-Driven Multi-Precision Weight Quantization for LLMs
StagQ is a multi‑precision weight format for large language models that uses a 2‑bit group‑wise affine base followed by optional 1‑bit refinement planes. Each supported precision can be read as a prefix of the main stream, decoded via a shared affine map without per‑weight lookups, and a sparse side record stores the few weights that the grid handles poorly. Experiments show that StagQ outperforms baseline multi‑precision schemes on Llama‑3.1‑8B, Phi‑4, and OLMo‑2‑7B across various bit‑widths, and its GPU kernel is faster than baseline kernels for most shape‑precision combinations.
arXiv Machine Learning
5d ago
CurveTQ: Rotation-Free Trellis Quantization of LLM Weights via Curvature-Weighted Search
arXiv:2610.09212v1 Announce Type: new Abstract: The best two-bit weight quantizers for large language models, such as QTIP and Proteus, rotate each weight matrix by a random orthogonal transform, whi...
arXiv Machine Learning
Jul 9
FPTQuant: Function-Preserving Transforms for LLM Quantization
arXiv:2506. 04985v2 Announce Type: replace Abstract: Large language models (LLMs) require substantial compute, and thus energy, at inference time.
arXiv AI
Jul 23
MoA-Structured Decode Attention DNF Derivation, KV-Cache Accumulation, GQA/MQA, and OpenACC Kernel
arXiv:2607. 19456v1 Announce Type: cross Abstract: We derive four memory-optimal inference artifacts for transformer attention using the Mathematics of Arrays (MoA), each following directly from the forward-pass Denotational Normal Form (DNF) of with the query-row index fixed to the current decode step.