@article{sparseaccelerateefficientlongcontext,
  title = {SparseAccelerate: Efficient Long-Context Inference for Mid-Range GPUs},
  author = {James Vo},
  year = {2024},
  eprint = {2412.06198},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2412.06198v1},
}