Kenny Falkær Olsen's starred repositories
matmulfreellm
Implementation for MatMul-free LM.
vdirsyncer
📇 Synchronize calendars and contacts.
ThunderKittens
Tile primitives for speedy kernels
flash-linear-attention
Efficient implementations of state-of-the-art linear attention models in Pytorch and Triton
awesome-ssm-ml
Reading list for research topics in state-space models
audioset-processing
Toolkit for downloading and processing Google's AudioSet dataset.
Diffusion2GAN
Website source files for Diffusion2GAN Project.
flash-linear-rnn
Implementations of various linear RNN layers using pytorch and triton
log-wmse-audio-quality
logWMSE, an audio quality metric with support for digital silence target. Useful for evaluating audio source separation systems, even when there are many audio tracks or stems.
torch-log-wmse
logWMSE, an audio quality metric & loss function with support for digital silence target. Useful for training and evaluating audio source separation systems.