English
Related papers

Related papers: Flash-LLM: Enabling Cost-Effective and Highly-Effi…

200 papers

Sampling from a categorical distribution is mathematically simple, but in large-vocabulary decoding, it often triggers extra memory traffic and extra kernels after the LM head. We present FlashSampling, an exact sampling primitive that…

Machine Learning · Computer Science 2026-05-14 Tomas Ruiz , Zhen Qin , Yifan Zhang , Xuyang Shen , Yiran Zhong , Mengdi Wang

Transformer-based large language models (LLMs) are comprised of billions of parameters arranged in deep and wide computational graphs, but it is not clear that they exploit their full capacity for all inputs. We introduce the s-Trace method…

Computation and Language · Computer Science 2026-05-27 Corentin Kervadec , Iuliia Lysova , Iuri Macocco , Marco Baroni , Gemma Boleda

Various Large Language Models~(LLMs) from the Generative Pretrained Transformer(GPT) family have achieved outstanding performances in a wide range of text generation tasks. However, the enormous model sizes have hindered their practical use…

Computation and Language · Computer Science 2024-04-24 Hang Shao , Bei Liu , Bo Xiao , Ke Zeng , Guanglu Wan , Yanmin Qian

The rapid development of the Transformer-based Large Language Models (LLMs) in recent years has been closely linked to their ever-growing and already enormous sizes. Many LLMs contain hundreds of billions of parameters and require dedicated…

Computation and Language · Computer Science 2025-02-26 Mahsa Salmani , Ilya Soloveychik

As they become more capable, large language models (LLMs) have continued to rapidly increase in size. This has exacerbated the difficulty in running state of the art LLMs on small, edge devices. Standard techniques advocate solving this…

Inference-time scaling trades efficiency for increased reasoning accuracy by generating longer or more parallel sequences. However, in Transformer LLMs, generation cost is bottlenecked by the size of the key-value (KV) cache, rather than…

Machine Learning · Computer Science 2025-11-10 Adrian Łańcucki , Konrad Staniszewski , Piotr Nawrot , Edoardo M. Ponti

Deploying large language models (LLMs) for long-context inference remains challenging due to their substantial memory and computational demands. While techniques such as Key-Value (KV) cache compression are designed to reduce memory usage,…

Computation and Language · Computer Science 2025-09-25 Jing Xiong , Jianghan Shen , Fanghua Ye , Chaofan Tao , Zhongwei Wan , Jianqiao Lu , Xun Wu , Chuanyang Zheng , Zhijiang Guo , Min Yang , Lingpeng Kong , Ngai Wong

The increasing adoption of large language models (LLMs) necessitates inference serving systems that can deliver both high throughput and low latency. Deploying LLMs with hundreds of billions of parameters on memory-constrained GPUs exposes…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-03-10 Bowen Pang , Kai Li , Feifan Wang

Inference in diffusion large language models (dLLMs) is computationally expensive, as full self-attention must be repeatedly executed at each step of the denoising process without KV cache. Recent sparse attention methods for dLLMs mitigate…

Computation and Language · Computer Science 2026-05-21 Yanyi Lyu , Letian Chen , Futing Sun , Miao Zhang , Weili Guan , Liqiang Nie

Recently, large language models (LLMs) have demonstrated superior performance across various tasks by adhering to scaling laws, which significantly increase model size. However, the huge computation overhead during inference hinders the…

Computation and Language · Computer Science 2024-12-17 Zekai Li , Jintu Zheng , Ji Liu , Han Liu , Haowei Zhu , Zeping Li , Fuwei Yang , Haiduo Huang , Jinzhang Peng , Dong Li , Lu Tian , Emad Barsoum

Many recent GPUs feature matrix multiplication engines (aka Tensor Core Units or TCUs) that perform small fixed-size matrix-matrix products at very high throughput. They have been used very effectively to speed up dense matrix-matrix…

Performance · Computer Science 2025-11-25 Lizhi Xiang , Omid Asudeh , Gerald Sabin , Aravind Sukumaran-Rajam , P. Sadayappan

Large language models have led to state-of-the-art accuracies across a range of tasks. However, training these models efficiently is challenging for two reasons: a) GPU memory capacity is limited, making it impossible to fit large models on…

Large Language Models (LLMs) are now integral across various domains and have demonstrated impressive performance. Progress, however, rests on the premise that benchmark scores are both accurate and reproducible. We demonstrate that the…

Computation and Language · Computer Science 2025-10-28 Jiayi Yuan , Hao Li , Xinheng Ding , Wenya Xie , Yu-Jhe Li , Wentian Zhao , Kun Wan , Jing Shi , Xia Hu , Zirui Liu

Efficient inference of Deep Neural Networks (DNNs) on resource-constrained edge devices is essential. Quantization and sparsity are key techniques that translate to repetition and sparsity within tensors at the hardware-software interface.…

Machine Learning · Computer Science 2025-05-07 Sachit Kuhar , Yash Jain , Alexey Tumanov

Training Large Language Models(LLMs) is one of the most compute-intensive tasks in high-performance computing. Predicting end-to-end training time for multi-billion parameter models distributed across hundreds of GPUs remains challenging…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-09-30 Biyao Zhang , Mingkai Zheng , Debargha Ganguly , Xuecen Zhang , Vikash Singh , Vipin Chaudhary , Zhao Zhang

Large Language Models (LLMs), while demonstrating remarkable capabilities across various applications, present significant challenges during inference due to their substantial model size, especially when deployed on edge devices. Activation…

Machine Learning · Computer Science 2025-04-29 Zhenyu Zhang , Zechun Liu , Yuandong Tian , Harshit Khaitan , Zhangyang Wang , Steven Li

The resource requirements of neural networks can be significantly reduced through pruning - the removal of seemingly less important parameters. However, for LLMs, full retraining to recover pruning-induced performance degradation is often…

Machine Learning · Computer Science 2026-02-03 Max Zimmer , Christophe Roux , Moritz Wagner , Deborah Hendrych , Sebastian Pokutta

Efficient large-scale inference of transformer-based large language models (LLMs) remains a fundamental systems challenge, frequently requiring multi-GPU parallelism to meet stringent latency and throughput targets. Conventional tensor…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-02-10 Chong Wang , Nan Du , Tom Gunter , Tao Lei , Kulin Seth , Senyu Tong , Jianyu Wang , Guoli Yin , Xiyou Zhou , Kelvin Zou , Ruoming Pang

The computational challenges of Large Language Model (LLM) inference remain a significant barrier to their widespread deployment, especially as prompt lengths continue to increase. Due to the quadratic complexity of the attention…

As large language models (LLMs) continue to grow in size, distributed inference has become increasingly important. Model-parallel strategies must now efficiently scale not only across multiple GPUs but also across multiple nodes. In this…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-21 Prajwal Singhania , Siddharth Singh , Lannie Dalton Hough , Akarsh Srivastava , Harshitha Menon , Charles Fredrick Jekel , Abhinav Bhatele