arXiv:2610.27699v1 Announce Type: new Abstract: Low-bit quantization reduces the memory footprint of large language models, but preserving accuracy with efficient training remains challenging. Scalar...
arXiv:2607. 02893v1 Announce Type: new Abstract: Low-bit quantization shrinks language models but treats precision as a single global hyper-parameter: every weight uses the same bit-width.
arXiv:2610.15384v1 Announce Type: cross Abstract: Compressing the key-value (KV) cache is essential for serving long-context large language models (LLMs) under memory constraints. While current scala...
MRVQ (Matryoshka Residual Vector Quantization) is a single post‑hoc residual quantizer designed for frozen embeddings that can be truncated to support any combination of embedding dimension and code rate. By dropping residual stages or embedding coordinates, MRVQ provides a single resident artifact that serves all evaluated (dimension, rate) pairs, achieving the lowest memory usage among tested designs. Although it uses 17.8–22.0× less memory than three separately trained QINCo2 indices and 1.89–2.02× less than a lean shared‑model steelman, it trades off a small drop in nDCG@10 on FiQA compared to per‑rate QINCo2, yet still outperforms PQ, OPQ, and AdANNS‑OPQ at matched code size.
arXiv:2610.14745v1 Announce Type: new Abstract: Extreme low-bit weight-only quantization is an effective approach to reducing the deployment costs of large language models. Below 3 bits, scalar quant...
The paper introduces a multi‑shell decoder for Leech‑lattice vector quantization, achieving the best reported 2‑bit quality under its evaluation protocol. It presents a GPU‑friendly layout that fuses dequantization with matrix‑vector multiplication, demonstrating significant speed and memory advantages over traditional one‑hot masks and other 4‑bit methods. Experiments show the new kernel outperforms baseline approaches across multiple model sizes, with measurable gains in throughput and reduced byte traffic.
arXiv:2610. 23796v1 Announce Type: new Abstract: Transformer prefill reuses weights across tokens and is dominated by matrix multiplication and activation data movement; single-token decode has limited reuse and is dominated by weight and KV-cache reads.
arXiv:2607. 07144v1 Announce Type: new Abstract: The key-value (KV) cache dominates the memory cost of long-context autoregressive inference, and a growing body of work compresses it through quantization, eviction, or offloading.
arXiv:2605.19660v3 Announce Type: replace Abstract: The rapid advancement toward long-context reasoning and multi-modal intelligence has made the memory footprint of the Key-Value (KV) cache a domina...
arXiv:2610.02598v1 Announce Type: new Abstract: Deploying LLMs on consumer-grade GPUs with insufficient memory to hold their weights can result in prohibitively slow inference, because decoding repea...
arXiv:2610.03027v1 Announce Type: cross Abstract: The key-value (KV) cache becomes a major memory bottleneck in long-context LLM inference, placing substantial pressure on memory capacity and bandwid...
The paper introduces the concept of Information Capacity (IC) to quantify how much bandwidth savings a unit of decoder compute can achieve in generative video compression (GVC). By modeling reconstruction quality as a two‑factor power law in data rate and compute, the authors fit measured DISTS of two GVC decoders with high accuracy and define IC as the negative logarithmic slope along an iso‑quality contour. IC is dimensionless, enabling architecture‑agnostic comparisons and revealing that a 14B decoder trades compute for rate far more efficiently than a 1.3B decoder, with significant variation across datasets.