PinnedLoading

1. flux-fp8-apiflux-fp8-apiPublic

   Flux diffusion model implementation using quantized fp8 matmul & remaining layers use faster half precision accumulate, which is ~2x faster on consumer devices.

   Python 254 35

2. torch-cublas-hgemmtorch-cublas-hgemmPublic

   PyTorch half precision gemm lib w/ fused optional bias + optional relu/gelu

   Cuda 55 3

3. torch-bnb-fp4torch-bnb-fp4Public

   Faster Pytorch bitsandbytes 4bit fp4 nn.Linear ops

   Python 27

4. functisfunctisPublic

   Universal image reader designed for seamless reading of images into multiple formats, including PIL Images, Torch Tensors, and NumPy arrays.

   Python 2

5. denoisemojidenoisemojiPublic

   command-line tool that allows you to create a pseudo diffusion denoised emoji gif from a PNG/WEBP/JPG image.

   Python 10

6. electron-G14Controlelectron-G14ControlPublic

   Electron desktop application replacement for G14ControlR3.

   TypeScript 207 27