@article{flashformerwholemodelkernelsforefficient, title = {FlashFormer: Whole-Model Kernels for Efficient Low-Batch Inference}, author = {Aniruddha Nrusimha and William Brandon and Mayank Mishra and Yikang Shen and Rameswar Panda and Jonathan Ragan-Kelley and Yoon Kim}, year = {2025}, eprint = {2505.22758}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.22758v1}, }