arXiv:2604. 09558v2 Announce Type: replace-cross Abstract: With the widening gap between compute and memory operation latencies, data movement optimizations have become increasingly important for DNN compilation.
By Muyan Hu, Ahan Gupta, Jiachen Yuan, Vima Gupta, Taeksang Kim, Xin Xu, Janardhan Kulkarni, Ofer Dekel, Vikram Adve, Charith Mendis
arXiv:2512. 22219v2 Announce Type: replace-cross Abstract: We introduce Mirage Persistent Kernel (MPK), the first compiler and runtime system that automatically transforms multi-GPU model inference into a single high-performance mega-kernel.
By Xinhao Cheng, Zhihao Zhang, Yu Zhou, Jianan Ji, Jinchen Jiang, Zepeng Zhao, Ziruo Xiao, Zihao Ye, Yingyi Huang, Ruihang Lai, Hongyi Jin, Bohan Hou, Mengdi Wu, Yixin Dong, Anthony Yip, Zihao Ye, Songting Wang, Wenqin Yang, Xupeng Miao, Tianqi Chen, Zhihao Jia
arXiv:2511. 10480v3 Announce Type: replace-cross Abstract: Optimizing the performance of large language models (LLMs) on large-scale AI training and inference systems requires a scalable and expressive mechanism to model distributed workload execution.
By Changhai Man, Joongun Park, Hanjiang Wu, Huan Xu, Srinivas Sridharan, Tushar Krishna
This survey reviews tensor methods applied to large language models, framing them through a seven‑stage lifecycle (tokenization, embeddings, pre‑training, adaptation, compression, inference, interpretability) and a component view (embeddings, attention, feed‑forward networks). It offers unified notation, theoretical foundations, and comparative analyses of tensorization strategies for Transformer components, while highlighting evaluation protocol differences and model scale effects. The paper also introduces a new metric, ρ_gap, to quantify the gap between theoretical memory savings and actual system‑level speedup, and connects tensor techniques to related efficiency and probabilistic methods.
By Matvei Tarasov, Salman Ahmadi-Asl, Andre L. F. de Almeida, Andrzej Cichocki
DanLing NestedTensor is a PyTorch tensor abstraction that embeds multi‑ragged structure directly into the tensor, allowing packed values to carry partition information and logical dimension order. This design enables broadcasting, feature transformations, and reductions to automatically respect ragged axes while preserving the same representation through autograd and both eager and compiled execution. Benchmarks on an A100 show significant speedups—up to 3.39× over padding for BERT models and 2.40–4.32× for a Pairformer‑style workload—while dramatically reducing peak memory usage.
By Zhiyuan Chen
Large language models (LLMs) are built from structured high-dimensional objects such as token representations, weights, adaptation updates, caches, and activations, whose multilinear structure is unde...