Maxtimer97's repositories
flash_linear
Efficient implementations of state-of-the-art linear attention models in Pytorch and Triton
MIT000
lineargru
Implementation for MatMul-free LM.
Apache-2.0000
Apache-2.0000
pytorch_mamba
A simple and efficient Mamba implementation in PyTorch and MLX.
MIT000
MIT000
GPL-3.0000