@article{kernelloopingeliminatingsynchronization, title = {Kernel Looping: Eliminating Synchronization Boundaries for Peak Inference Performance}, author = {David Koeplinger and Darshan Gandhi and Pushkar Nandkar and Nathan Sheeley and Matheen Musaddiq and Leon Zhang and Reid Goodbar and Matthew Shaffer and Han Wang and Angela Wang and Mingran Wang and Raghu Prabhakar}, year = {2024}, eprint = {2410.23668}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2410.23668v1}, }