@article{paralleltracktransformersenablingfastgpu, title = {Parallel Track Transformers: Enabling Fast GPU Inference with Reduced Synchronization}, author = {Chong Wang and Nan Du and Tom Gunter and Tao Lei and Kulin Seth and Senyu Tong and Jianyu Wang and Guoli Yin and Xiyou Zhou and Kelvin Zou and Ruoming Pang}, year = {2026}, eprint = {2602.07306}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.07306}, }