Aug 2026· 2 citations· ⚡ 1 influential· 23 references
Computer Science
TL;DR
OptR is proposed, an output-aware rotation method that minimizes post-W_O$ attention-output error and applies an attention-equivalent key reparameterization to reduce large channel-wise offsets without changing the softmax distribution.
Abstract
The key-value (KV) cache has become a major memory and bandwidth bottleneck in long-context large language model inference, making ultra-low-bit quantization increasingly important. However, existing rotation-based INT2 methods optimize cache statistics or proxy errors before the complete attention readout, even though the model is ultimately affected by the error propagated through attention and the output projection $W_O$. To address this mismatch, we propose \textit{OptR}, an output-aware rotation method that minimizes post-$W_O$ attention-output error. OptR decomposes the post-$W_O$ attention-output error into key- and value-induced terms and learns per-head orthogonal corrections through the full INT2 quantization and attention path. OptR further applies an attention-equivalent key reparameterization to reduce large channel-wise offsets without changing the softmax distribution. Across three models and five reasoning and coding benchmarks, OptR consistently improves both QuaRot and OSCAR and strengthens long-context retrieval, while preserving the paged KV-cache format with negligible inference overhead.
Attention-Aware Transform Coding is introduced, which allocates bits over a calibration set to minimize attention-aware distortion and achieves near-lossless accuracy at approximately $5.8\times compression.
Hannah Laus, C. M. Verdun, Hao Wang et al.· 1 citation
The results show that low-rank projection adaptation can recover held-out quality across fixed cache formats, while perplexity recovery need not restore long-context retrieval.
The key-value (KV) cache becomes a major memory bottleneck in long-context LLM inference, placing substantial pressure on memory capacity and bandwidth. To mitigate this bottleneck, vector quantization (VQ) has emerged as a promising approach for aggressive KV cache compression. However, existing VQ methods degrade sub...
This work introduces WUSH-KV, which adapts WUSH, which constructs a data-aware transform from the second-order statistics of both factors in a matrix product to reduce quantization error and achieves the lowest end-to-end perplexity among other tested transforms.
Jiale Chen, Vage Egiazarian, Eldar Kurtic et al.· 0 citations
Multi-Head Latent Attention (MLA) enables expressive multi-head attention with compact caches for its content and decoupled RoPE paths, yet cache memory still scales linearly with context length and batch size. In this work, we establish a systematic model of MLA's dual-path quantization errors, characterizing their di...
Zun-Hai Su, Yuxuan Sun, Jian-Chao Tan et al.· 0 citations
Design rules and a reproducible evaluation protocol are contributed that jointly report quality, memory, and end-to-end speed, and a foundation for automated pipeline search under realistic single-GPU constraints is provided.
Hong-Yu Yu, Yihan Shen· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduOct 13, 2026
Machine-learning networks can learn without detailed instructions from a designer. Those that do may offer insight into how the brain reorganizes itself during learning.
MIT News · Artificial Intelligence· news.mit.eduSep 29, 2026
Professor Sherry Turkle’s new book, “Artificial Intimacy,” offers a withering critique of chatbots and the antisocial dynamics she believes they encourage.