English
Related papers

Related papers: Dissecting Outlier Dynamics in LLM NVFP4 Pretraini…

200 papers

Attention, as a core layer of the ubiquitous Transformer architecture, is the bottleneck for large language models and long-context applications. While FlashAttention-3 optimized attention for Hopper GPUs through asynchronous execution and…

Computation and Language · Computer Science 2026-03-06 Ted Zadouri , Markus Hoehnerbach , Jay Shah , Timmy Liu , Vijay Thakkar , Tri Dao

Recent advances in deep learning methods such as LLMs and Diffusion models have created a need for improved quantization methods that can meet the computational demands of these modern architectures while maintaining accuracy. Towards this…

Machine Learning · Computer Science 2024-04-02 Haihao Shen , Naveen Mellempudi , Xin He , Qun Gao , Chang Wang , Mengni Wang

KV cache quantization reduces the memory cost of long-context LLM inference, but introduces approximation error that is typically validated only empirically. Existing systems rely on average-case robustness, with no mechanism to detect or…

Machine Learning · Computer Science 2026-05-21 Dean Calver

Multi-head Latent Attention (MLA) significantly reduces KVCache memory usage in Large Language Models while introducing substantial computational overhead and intermediate variable expansion. This poses challenges for efficient hardware…

Machine Learning · Computer Science 2025-10-23 Qichen Liao , Chengqiu Hu , Fangzheng Miao , Bao Li , Yiyang Liu , Junlong Lyu , Lirui Jiang , Jun Wang , Lingchao Zheng , Jun Li , Yuwei Fan

Large language models require significant computational resources for deployment, making quantization essential for practical applications. However, the main obstacle to effective quantization lies in systematic outliers in activations and…

Machine Learning · Computer Science 2025-11-25 Cuong Pham , Hoang Anh Dung , Cuong C. Nguyen , Trung Le , Gustavo Carneiro , Jianfei Cai , Thanh-Toan Do

Modern Large Language Model serving system batches multiple requests to achieve high throughput, while batching attention operations is challenging, rendering memory bandwidth a critical bottleneck. The community relies on high-end GPUs…

Hardware Architecture · Computer Science 2025-05-15 Minsu Kim , Seongmin Hong , RyeoWook Ko , Soongyu Choi , Hunjong Lee , Junsoo Kim , Joo-Young Kim , Jongse Park

Outliers in weights and activations pose a key challenge for fixed-point quantization of neural networks. While they can be addressed by fine-tuning, this is not practical for ML service providers (e.g., Google or Microsoft) who often…

Machine Learning · Computer Science 2021-05-28 Ritchie Zhao , Jordan Dotzel , Zhanqiu Hu , Preslav Ivanov , Christopher De Sa , Zhiru Zhang

The quadratic computational complexity of softmax transformers has become a bottleneck in long-context scenarios. In contrast, linear attention model families provide a promising direction towards a more efficient sequential model. These…

Computation and Language · Computer Science 2026-02-04 Difan Deng , Andreas Bentzen Winje , Lukas Fehring , Marius Lindauer

Transformer architectures have achieved remarkable success in various domains. While efficient alternatives to Softmax Attention have been widely studied, the search for more expressive mechanisms grounded in theoretical insight-even at…

Machine Learning · Computer Science 2025-10-03 Yifei Zuo , Yutong Yin , Zhichen Zeng , Ang Li , Banghua Zhu , Zhaoran Wang

Deep Learning Accelerators are prone to faults which manifest in the form of errors in Neural Networks. Fault Tolerance in Neural Networks is crucial in real-time safety critical applications requiring computation for long durations. Neural…

Machine Learning · Computer Science 2021-06-01 Vasisht Duddu , D. Vijay Rao , Valentina E. Balas

Training large language models (LLMs) models directly in low-precision offers a way to address computational costs by improving both throughput and energy efficiency. For those purposes, NVIDIA's recent Blackwell architecture facilitates…

Multi-agent LLM systems on edge devices face a memory management problem: device RAM is too small to hold every agent's KV cache simultaneously. On Apple M4 Pro with 10.2 GB of cache budget, only 3 agents fit at 8K context in FP16. A…

Machine Learning · Computer Science 2026-03-06 Yakov Pyotr Shkolnikov

Quantization techniques, including quantization-aware training (QAT) and post-training quantization (PTQ), have become essential for inference acceleration of image super-resolution (SR) networks. Compared to QAT, PTQ has garnered…

Computer Vision and Pattern Recognition · Computer Science 2025-11-04 Hailing Wang , jianglin Lu , Yitian Zhang , Yun Fu

Looped Transformers (LT) have emerged as a powerful architecture by iterating their layers multiple times before decoding the final token. However, pairing them with full attention retains quadratic complexity, making them computationally…

Machine Learning · Computer Science 2026-05-26 Chunyuan Deng , Yizhe Zhang , Rui-Jie Zhu , Yuanyuan Xu , Jiarui Liu , T. S. Eugene Ng , Hanjie Chen

Transformers have emerged as the dominant neural-network architecture, achieving state-of-the-art performance in language processing and computer vision. At the core of these models lies the attention mechanism, which requires a nonlinear,…

Machine Learning · Computer Science 2026-04-13 Luis Mickeler , Kai Lion , Alfonso Nardi , Jost Kellner , Pierre Didier , Bhavin J. Shastri , Niao He , Rachel Grange

Although quantization for linear layers has been widely used, its application to accelerate the attention process remains limited. To further enhance the efficiency of attention computation compared to SageAttention while maintaining…

Machine Learning · Computer Science 2025-10-02 Jintao Zhang , Haofeng Huang , Pengle Zhang , Jia Wei , Jun Zhu , Jianfei Chen

As Large Language Models make a breakthrough in natural language processing tasks (NLP), multimodal technique becomes extremely popular. However, it has been shown that multimodal NLP are vulnerable to adversarial attacks, where the outputs…

Computation and Language · Computer Science 2026-03-16 Hao Wang , Jinzhe Jiang , Xin Zhang , Chen Li

Linear attention reduces the quadratic cost of softmax attention to $\mathcal{O}(T)$, but its memory state grows as $\mathcal{O}(T)$ in Frobenius norm, causing progressive interference between stored associations. We introduce…

Machine Learning · Computer Science 2026-05-13 Vishal Pandey , Gopal Singh

Large language models (LLMs) have grown beyond the memory capacity of single GPU devices, necessitating quantization techniques for practical deployment. While NF4 (4-bit NormalFloat) quantization enables 4$\times$ memory reduction,…

Machine Learning · Computer Science 2026-04-06 Xiangbo Qi , Chaoyi Jiang , Murali Annavaram

Lightweight design of Convolutional Neural Networks (CNNs) requires co-design efforts in the model architectures and compression techniques. As a novel design paradigm that separates training and inference, a structural re-parameterized…

Computer Vision and Pattern Recognition · Computer Science 2024-02-13 Muqun Niu , Yuan Ren , Boyu Li , Chenchen Ding
‹ Prev 1 3 4 5 6 7 10 Next ›