@article{acceleratingatritonfusedkernelforw4a16,
  title = {Accelerating a Triton Fused Kernel for W4A16 Quantized Inference with SplitK work decomposition},
  author = {Adnan Hoque and Less Wright and Chih-Chieh Yang and Mudhakar Srivatsa and Raghu Ganti},
  year = {2024},
  eprint = {2402.00025},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2402.00025v2},
}