Quantization has been widely adopted in LLM training and inference to reduce cost and improve efficiency. However, low-bit quantization of the \emph{attention} module often introduces large errors at very low bit-widths, causing performance degradation. Existing methods mainly rely on smoothing techniques to handle outliers, while we propose a hybrid quantization design to better balance accuracy and efficiency. Specifically, we propose \textbf{HyQuant}, an efficient hybrid quantization framework for LLM attention. HyQuant quantizes most attention states into low-bit formats while retaining a small set of vertical-line tokens and local-window states in high precision. These accuracy-critical regions are selected using lightweight vertical-line-aware attention-pattern signals, reducing quantization error with limited overhead. In the Prefill stage, HyQuant uses a hybrid-precision quantized attention operator that preserves vertical-line tokens and a local sliding window in full precision while quantizing the remaining context. In the Decode stage, HyQuant applies the same principle to KV-cache compression and fuses KV dequantization with attention computation to improve memory and hardware efficiency. Across diverse tasks, models, and datasets, HyQuant maintains nearly lossless accuracy with an extremely simple design, demonstrating the efficiency and practical feasibility of hybrid quantization for LLM attention. Code is available at: https://github.com/jerrysfls/HyQuant .
Mihailo Ilić, Miloš Savić, Vladimir Kurbalija +3cs.LG
Outlier detection in decentralized data environments is a challenging task for many machine learning implementations, particularly in settings where data cannot be shared. Recently, there have been advances in federated outlier detection, some of which are based on the use of autoencoder networks. The introduction of attention mechanisms to autoencoders boosts their efficiency. However, the application of attention-based models in federated learning remains underdeveloped due to the absence of proper aggregation functions for these types of networks. In our work, we propose two novel aggregation functions tailored for attention-based autoencoders, which better preserve the learned information stored within the memory modules of these networks. We evaluated our approach on the KDDCUP10 dataset, and we showed that the proposed methods achieve up to 2.9\% and 5.1\% better results for F1 score and AUC ROC respectively when compared to traditional autoencoders.
Transformer architectures form the foundation of modern natural language processing, yet the Key-Value (KV) cache introduces substantial memory and bandwidth overhead during long-context generation, increasingly bottlenecking large-scale deployment. We propose Keyless Attention, a novel attention mechanism that replaces the conventional key projection with a dedicated value-space routing projection, eliminating key representations from the attention computation entirely and yielding a Value-Only Cache that reduces KV-cache memory by 50% while improving decode throughput. Experiments across multiple models and architectures demonstrate that Keyless Attention achieves comparable perplexity and downstream task performance to standard QKV attention, while consistently reducing KV-cache memory by 50%. Furthermore, Keyless Attention exhibits slower validation loss degradation after the best epoch, indicating improved robustness against overfitting. Ablation studies confirm that the dedicated value-space routing projection is critical, with Keyless Attention outperforming KV-sharing methods that eliminate the key cache without replacing its routing role. Experiments in the pretraining regime further confirm the viability of Keyless Attention in industrial settings.
Ziqun Chen, Ming Wu, Michael Heinrich +4cs.LG cs.AI
Computation integrity of remote large language model (LLM) serving can be questionable. For conventional deep neural networks (DNNs), the existing TEE-shielded DNN partitioning (TSDP) approach uses Trusted Execution Environment (TEE) to compute non-linear components and verify the integrity of linear components offloaded to an untrusted GPU. However, directly applying TSDP to Transformer-based LLMs incurs significant TEE computation and TEE-GPU communication overhead. This paper presents Communication-efficient TEE-GPU Attention (\textsc{VeriAttn}) for accelerating verifiable LLM inference. \textsc{VeriAttn} offloads both linear and non-linear computations of attention to the GPU, while TEE performs verification. Moreover, for prefill, \textsc{VeriAttn} uses a two-level pipeline to overlap data movement, TEE pre-/post-processing, and GPU computation. For decoding, when the key-value cache exceeds available GPU memory, \textsc{VeriAttn} partitions attention across TEE and GPU to reduce repeated key-value transfers. Evaluation on an Intel TDX platform shows that \textsc{VeriAttn} achieves 2.60-3.38$\times$ and 3.86-5.42$\times$ acceleration over TSDP for 6k-token prompts and 10k-token outputs during prefill and decoding, respectively.
We address transformer attention on energy-constrained physical substrates. Softmax attention requires exponentiation and global reduction, operations with high energy cost on von Neumann hardware and no natural physical analog. We show that Kuramoto synchronization dynamics (which arise in electrical, mechanical, superconducting, and charge-density-wave oscillator arrays, among other physical systems) implement a well-defined attention operation without either. The resulting mechanism, fixed-query oscillator attention, replaces softmax's arithmetic with the equilibration of a gradient flow on the sphere: queries are learned anchors fixed on the sphere, and free oscillators evolve under Kuramoto-Lohe dynamics until they settle at positions encoding attention weights via cosine similarity. Because the computation is equilibration, it requires no exponentiation; the only global operation is an affine normalization at readout. The fixed point is provably unique and globally attractive from almost every initial condition, a guarantee that holds across every physical realization. Empirically, at the minimal hardware configuration (oscillator dimension $d_{\mathrm{osc}}$ = 2), oscillator attention outperforms softmax on keyword spotting (+1.00 pp) and on subject-verb agreement (+5.27 pp on hard sentences, with zero training failures versus one in five for softmax). On causal language modeling, where softmax retains an advantage, oscillator attention closes the gap as $d_{\mathrm{osc}}$ grows: from +11.09 PPL at $d_{\mathrm{osc}}$ = 2 to +2.98 PPL at $d_{\mathrm{osc}}$ = 32 on WikiText-2, and from +2.39 PPL at $d_{\mathrm{osc}}$ = 2 to +0.57 PPL at $d_{\mathrm{osc}}$ = 32 on TinyStories. The main objective of this work is not to replace softmax in software but to provide a mathematically grounded blueprint for accurate attention on physical substrates.
The attention mechanism is the dominant computational bottleneck in modern transformer-based AI. Its standard implementation incurs quadratic memory traffic in the sequence length~$n$, and DRAM accesses cost 100--1000$\times$ more energy than arithmetic operations on contemporary hardware, so any analysis focused solely on FLOP counts fundamentally mischaracterises the bottleneck. We present a Mathematics of Arrays (MoA) reformulation of scaled dot-product attention and its numerically stable softmax, deriving a Denotational Normal Form (DNF) that eliminates all intermediate arrays -- including the implicit transposed-key buffer and every softmax temporary -- by algebraic construction rather than empirical tuning. The DNF achieves $O(n_{dk} + n{_{dv}})$ data movement versus $O(n^2 + n_{dk} + n_{dv})$ for the standard implementation, where $n$ is the sequence length, $dk$ is the key dimensionality and $dv$ the value dimensionality, and is verified numerically against PyTorch at full double-precision floating-point on concrete inputs. Unlike hardware-specific accelerators or empirical tiling schemes such as FlashAttention, MoA simultaneously provides array fusion, shape-transformation correctness, and predictive cost models from a single algebraic framework. Memory minimality is a theorem established before any code is written. A predictive performance model projects $2$--$100\times$ speedup and $2$--$50\times$ energy reduction, with the advantage widening at exascale. The derivation establishes a formally verified pipeline from Python specification through (ONF) Operational Normal Form, and dimension-lifted hardware mapping, providing performance-portable AI kernels of direct relevance to DARPA edge-deployment and DOE exascale priorities.
Key-value (KV) caching accelerates inference of large language models (LLMs) by reusing past computations for generated tokens. Its importance becomes even greater in long-context applications such as retrieval-augmented generation (RAG) and in-context learning (ICL). However, conventional KV caching embeds positional information directly into the cache, limiting its reusability. Existing solutions either restrict reuse to prefixes or require expensive memory materialization for positional re-encoding. We introduce LazyAttention, a novel attention mechanism that kernelizes deferred positional encoding to enable zero-copy, position-agnostic KV reuse. By adjusting positional encoding within attention kernels on-the-fly, LazyAttention resolves the materialization bottleneck, allowing a single physical KV copy to serve multiple logical requests at arbitrary positions. Leveraging attention kernels tailored for prefilling and decoding, our system achieves significant efficiency improvements: under skewed document distributions, it reduces time-to-first-token (TTFT) by 1.37$\times$ and increases inference throughput by 1.40$\times$ compared to the state-of-the-art Block-Attention, while maintaining comparable output quality.