The paper addresses the problem of non‑deterministic outputs from large language models (LLMs) when run on different GPU architectures, caused by floating‑point non‑associativity and hardware‑dependent kernel choices. It proposes a set of fixed‑configuration fused‑upcast GEMM kernels that load 16‑bit weights, upcast to FP32, and perform IEEE‑754 compliant reductions in a problem‑shape‑dependent order, ensuring identical linear‑layer outputs across NVIDIA Ampere, Ada, and Hopper GPUs. The new approach achieves 1.17–3.1× faster end‑to‑end performance than existing solutions and halves weight‑memory traffic while maintaining cross‑architecture reproducibility.
By Liam Cooper, Shinnung Jeong, Hyeran Jeon, Jeffrey Young, Hyesoon Kim
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. 19431v1 Announce Type: cross Abstract: Bit-serial accelerators exploit bit-level sparsity to reduce DNN inference cost, but existing designs exploit sparsity on only one operand, bounding the speedup.
By Varun Manjunath, Ruokai Yin, Donghyun Lee, Arkapravo Ghosh, Priyadarshini Panda
arXiv:2607. 28418v1 Announce Type: cross Abstract: Pruning is a promising approach for improving the efficiency of LLMs.
By Haozhe Hu, Hao Wu, Peiran Yin, Chao Han, Yunpu Ma, Xiaoyu Shen
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
arXiv:2606. 00144v1 Announce Type: cross Abstract: Speculative decoding speeds up autoregressive decoding by using a drafter to propose multiple tokens that a verifier validates in parallel.
By Liang He, Jingbo Wen, Qishi Zhan, Yixiong Chen, Kangning Cui, Qizhen Lan, Xilu Wang
SparseDitto is an agentic sparse compilation framework that jointly synthesizes representation, execution schedule, and hardware mapping for sparse matrix computations on GPUs. It uses structural analysis, a learned template-ranking prior, and LLM-guided lowering to generate CUDA code, with target-GPU profiling refining the plan. The framework supports multiple operators such as SpMV, SpMM, and SpGEMM, adapts to different hardware, and achieves significant speedups over cuSPARSE, including up to 146.61× on certain matrices and 3.39× acceleration for full-batch GCN training.
By Shiyang Li, Guangyan Sun, Jinwei Tang, Yanzhi Wang, Mingyi Hong, Caiwen Ding
arXiv:2605. 01910v2 Announce Type: replace-cross Abstract: Autoregressive decoding becomes bandwidth-limited at long contexts, as generating each token requires reading all $n_k$ key and value vectors from KV cache.
By Kyle Lee, Corentin Delacour, Kevin Callahan-Coray, Kyle Jiang, Can Yaras, Samet Oymak, Tathagata Srimani, Kerem Y. Camsari
arXiv:2608. 01536v1 Announce Type: cross Abstract: Large Language Models (LLMs) increasingly rely on sparsity to reduce inference cost, but most prior work targets a single sparsity source-either weight or activation-and optimizes for batched multi-user inference.
By Ruokai Yin, Priyadarshini Panda
arXiv:2608.30439v1 Announce Type: cross
Abstract: Inference with transformer-based large language models (LLMs) is often limited by the memory-bound KV cache and quadratic attention cost. State-space...
By Simon Richter, Ruhai Lin, Jason Yik, Taylor Kergan, Rui-Jie Zhu, Farshad Moradi, Jason Eshraghian
arXiv:2608.21157v1 Announce Type: cross
Abstract: High-performance GPU kernels underpin modern deep learning and scientific computing. As workloads become increasingly diverse and GPU hardware evolve...
By Jinghao Wang, Qiqi Gu, Chenpeng Wu, Jianguo Yao, Haibing Guan, Xijun Li
arXiv:2607. 16241v1 Announce Type: cross Abstract: Recent large language models (LLMs) can generate custom CUDA kernels that appear to outperform PyTorch on benchmarks such as KernelBench.
By Yunxiang Zhang (Xiangjun), Ping Yu (Xiangjun), Jianyu Wang (Xiangjun), Max (Xiangjun), Fan, Julian Reed, Azalia Mirhoseini, Will Su