arXiv:2608. 15602v1 Announce Type: cross Abstract: While binary quantization theoretically promises extreme compression and acceleration for Large Language Models (LLMs), existing research often overlooks the necessity of specialized hardware kernels, thus failing to unleash the full acceleration potential due to persistent reliance on expensive floating-point arithmetic or runtime dequantization overheads.
By Qingyao Yang, Runming Yang, He Xiao, Wendong Xu, Junyu Chen, Haobo Liu, Chenchen Ding, Ruihan Hu, Yik-Chung Wu, Ngai Wong
arXiv:2607. 25504v1 Announce Type: cross Abstract: Fine-grained weight pruning and activation sparsification have emerged as effective approaches for reducing the compute and memory cost of inference for Transformer models.
By Bowen Wang, Chi Zhang, Diyou Shen, Renzo Andri, Navaneeth Kunhi Purayil, Luca Benini
arXiv:2608. 00029v1 Announce Type: cross Abstract: The performance of deep learning models at scale relies heavily on how effectively high-level mathematical operations are mapped to underlying physical hardware.
By Adwaid Suresh, Aparna A, Harshini V M, Jona Delcy C A, Killi Uma Maheswara Rao, Ram Charan Golla, Surendra Vendra
arXiv:2506. 20686v2 Announce Type: replace-cross Abstract: Recent advances in biomolecular modeling have been catalyzed by models such as AlphaFold3 (AF3), which introduce science-informed changes to the transformer architecture.
By Hoa La, Ahan Gupta, Alex Morehead, Jianlin Cheng, Minjia Zhang
arXiv:2607. 08786v1 Announce Type: cross Abstract: With the growing deployment of large language models (LLMs), LLM inference cost has become a key challenge.
By Tao Lu, Haoyu Wang, Zonghui Wang, Keshen Xiang, Jiaheng Zhang, Wenzhi Chen
Semi-structured 2:4 sparsity is widely supported by modern accelerators, providing up to a 2x theoretical speedup. However, its strict 50% sparsity constraint often causes non-negligible accuracy degradation under post-training pruning.
The paper explores using large language models (LLMs) to replace traditional compiler backends, a process termed AI lowering. An LLM agent translates Triton kernels directly into NVIDIA PTX, achieving 0.83x–3.34x the performance of autotuned Triton on a variety of GPUs and ML kernels. The study also extends a PTX verifier to support modern GPU features, highlighting the potential for AI compilers to reduce engineering effort for new hardware.
By Fran\c{c}ois Costa, Charly Castes, Thomas Bourgeat, Azalia Mirhoseini
arXiv:2606. 10445v1 Announce Type: new Abstract: Semi-structured 2:4 sparsity is widely supported by modern accelerators, providing up to a 2x theoretical speedup.
By Jaeseong Lee, Seung-won Hwang, Samyam Rajbhandari
arXiv:2606. 31938v1 Announce Type: cross Abstract: Deploying Vision Transformer (ViT) models on edge platforms remains challenging due to their high computational demands and the architectural heterogeneity of modern hybrid ViT models, which incorporate both fully connected and convolutional layers.
By Hubert Dymarkowski, Xingjian Fu, Rappy Saha, Jude Haris, Jos\'e Cano
arXiv:2608.20725v1 Announce Type: cross
Abstract: Convolution is a principal computational bottleneck in deep neural networks, and its efficiency depends on tight integration between algorithms and G...
By Xiang Fu, Jixiang Ma, Xinpeng Zhang, Peng Zhao, Shuai Lu, Xu Tony Liu
arXiv:2606. 13894v1 Announce Type: cross Abstract: AdamW is a default optimizer for modern deep learning, but its first and second moment states add roughly two parameter-sized buffers to training memory.
By Nadav Benedek, Tomer Koren, Ohad Fried
arXiv:2604. 23466v2 Announce Type: replace Abstract: NVIDIA's CUDA Tile (CuTile) introduces a Python-based, tile-centric abstraction for GPU kernel development that aims to simplify programming while retaining Tensor Core and Tensor Memory Accelerator (TMA) efficiency on modern GPUs.
By Divakar Kumar Yadav, Tian Zhao, Deepak Kumar