This work proposes Adaptive Vector-Quantized (AVQ) Attention, which adaptively allocates codebook capacity based on attention importance and develops an implementation using custom Triton kernels that enables the full adaptive refinement process, including importance scoring, child codeword insertion, and parent contribution replacement, to be carried out within the tiled computation paradigm of Flash Attention with minimal overhead.
Abstract
The $\mathcal{O}(N^2)$ complexity of attention over $N$ tokens remains a computational bottleneck in transformer models. Vector-Quantized (VQ) attention reduces this to $\mathcal{O}(MN)$ by representing keys with $M$ codewords, but applies uniform codebook capacity regardless of where attention mass concentrates: high-attention regions of key space may be coarsely approximated while low-attention regions waste representational capacity. We propose Adaptive Vector-Quantized (AVQ) Attention, which adaptively allocates codebook capacity based on attention importance. Starting from a small set of codewords, our method identifies the most important codes during the forward pass and refines them with pre-learned child codewords, achieving fine-grained quantization where it matters most while maintaining coarse quantization elsewhere. We develop an implementation using custom Triton kernels that enables the full adaptive refinement process, including importance scoring, child codeword insertion, and parent contribution replacement, to be carried out within the tiled computation paradigm of Flash Attention with minimal overhead. Our approach maintains $\mathcal{O}(MN)$ complexity while achieving improved accuracy-efficiency trade-offs compared to fixed-codebook VQ-attention.
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.
Jiarui Ding, Bin Xing, Yu Zhang et al.· 0 citations
Video Diffusion Transformers (DiTs) spend most of their compute inside the Self-Attention operation, whose cost grows quadratically, $\mathcal{O}(n^2)$, with the number of latent tokens $n$. For the task of video generation, the token count is large, so this term dominates runtime and memory, and thereby caps the resolution and duration we can generate. Linear $\mathcal{O}(n)$ and low-rank $\mathcal{O}(nk)$ surrogates of Self-Attention trade the full softmax $QK^T$ for cheaper kernels, but rarely recover the original's expressivity, leaving a stubborn quality gap. Motivated by this, we propose SQuad, a Sub-Quadratic Attention Distillation framework that achieves a complexity of $\mathcal{O}(n\sqrt{n})$ in the resulting distilled Attention, naturally balancing the efficiency v/s expressivity trade-off. Instead of training our own Video DiT from scratch, which is prohibitively expensive, we fit a pretrained full softmax Self-Attention DiT into our proposed SQuad-Attention one by distilling the former in two stages: Flow-Matching Supervised Fine-Tuning (SFT), followed by improved Distribution Matching Distillation (DMD2) which additionally makes the sampling more efficient. On the Wan~2.2 5B text-to-video model, SQuAD matches the quadratic teacher on VBench ($83.20$ v/s $83.08$) while cutting the per-step per-block attention FLOPs by $\sim$$67\times$ and attention latency by $\sim$$11\times$, and end-to-end DiT latency by 2$\times$, all while also generating a video in only $6$ Neural Functional Evaluations (NFEs) instead of the default $100$.
Animesh Karnewar, Denis Korzhenkov, A. Habibian et al.· 0 citations
Across five models from 1B to 32B, SoftWater outperforms the released WaterSIC quantizer at matched head rates on 59 of 60 test points, using none of that pipeline's refinements and cutting head-induced KL by $6.5\times$--$8.3\times at 2 bits.
The quadratic $N\times N$ attention score matrix remains a central obstacle to extending Transformers to longer input lengths. Existing efficient attention methods usually reduce this bottleneck by either imposing sparsity, so that each query attends to only a small subset of keys, or by using low-rank/kernel sketches, so that global interactions are compressed into a lower-dimensional representation. We propose \emph{ELSAA}, an efficient low-rank and sparse approximation of attention. Importantly, ELSAA does \emph{not} decompose the learned projection or output matrices of the Transformer into sparse and low-rank factors. Instead, after dense projections produce $Q,K,V$, ELSAA approximates the induced attention score operator itself: a sparse branch captures selected high-similarity interactions, while a low-rank branch summarizes diffuse global interactions. Since the two branches can be normalized over supports with very different denominator mass, ELSAA introduces a denominator-aware fusion term that scales the sparse branch according to its estimated attention mass relative to the low-rank branch. This gives a practical framework for constructing low-rank and sparse attention outputs without materializing the full quadratic score matrix, aiming to enable longer-context training while preserving both sharp token-level interactions and broad contextual mixing.
Mahdi Heidari, Mohammad Mahdi Rahimi, Jaekyun Moon· arXiv.org· 0 citations
Low-bit attention accelerates Transformer inference by moving the $QK^\top$ and $PV$ matrix multiplications to FP8 or FP4 matrix engines. However, the softmax path often evaluates shifted-score exponentials in higher precision, forms a temporary probability block, and quantizes it before low-bit $PV$ multiplication. This exp-then-quantize path creates a mismatch between a high-precision probability producer and a low-bit matrix consumer. We propose EFQ-Softmax (Exp-Free Quantization for Softmax), a low-bit probability-generation method that directly maps shifted attention scores to block-scaled E2M1 operands. For each microscaling block, EFQ-Softmax selects an exponent-only scale from the local maximum, maps the shifted scores to a normalized residual domain, and generates nonnegative E2M1 probability codes using a single affine rule. The resulting operand is used consistently in both the $\widetilde{P}V$ numerator update and the $\widetilde{P}\mathbf{1}$ denominator update. The FlashAttention-style row-maximum update, historical rescaling, high-precision accumulation, and final normalization remain unchanged. We evaluate end-to-end quality on Qwen3-8B, Qwen3-VL-8B-Instruct, and WAN2.2-TI2V-5B, and separately measure kernel-level performance on the A5 vector unit. EFQ-Softmax improves the Qwen3-8B seven-task mean from 0.6749 with MXFP4 to 0.6773 and the Qwen3-VL nine-task mean from 0.7826 to 0.8000. On WAN2.2, it maintains temporal consistency and visual quality comparable to the FP16 and MXFP4 baselines under VBench. On the A5 vector unit, EFQ-Softmax reduces the vector-stage latency of the fused probability-generation kernel by 40.33% on average across sequence lengths from 16K to 128K. These results show that direct low-bit probability generation can replace the conventional exp-then-quantize path while preserving end-to-end model quality.
Haohui Han (Xi'an Jiaotong University), Yuming Wan (Huawei Technologies Co., Ltd) et al.· 0 citations
APT, a software-hardware co-designed accelerator for high-resolution DiTs that leverages attention probabilities as a unified importance metric to jointly optimize computation through fine-grained pruning and adaptive precision scaling, and is evaluated on SOTA DiT models including PixArt, Stable Diffusion 3, and FLUX.
Sungyeob Yoo, Seeyeon Kim, Joonyong Park et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
