From-scratch PyTorch implementation of Google's TurboQuant (ICLR 2026) for LLM KV cache compression. 5x compression at 3-bit with 99.5% attention fidelity.

Single Channel Speech Enhancement Methods and Toolbox

Room Impulse Response reconstruction with Physics Informed Neural Networks

Yet Another Document Translator

Audio text dataset for pytorch training based on webdataset.

Efficient Inference of Transformer models

Official PyTorch implementation of 'Rec-RIR: Monaural Blind Room Impulse Response Identification via DNN-based Reverberant Speech Reconstruction in STFT Domain'

Precision Alignment, Infinite Possibilities

🔥 Clone and recreate any website as a modern React app in seconds

Perceptual Quality Estimator for speech and audio

Official inference framework for 1-bit LLMs

CUDA Templates and Python DSLs for High-Performance Linear Algebra

Accessible large language models via k-bit quantization for PyTorch.

BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.

人人都能用英语