Showing 1-9 of 9 projects
A stable and secure container image mirror service to speed up image downloads for developers in China.
Ultra-efficient large language models (LLMs) for end devices, enabling fast on-device reasoning and inference.
DiffSinger is a singing voice synthesis system using a shallow diffusion mechanism, enabling efficient TTS and SVS.
A TypeScript loader for the esbuild bundler, which can speed up your Webpack builds.
Quantized attention that achieves 2-5x speedup over FlashAttention for language, image, and video models.
Implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference, for AI coding tools.
A Python library that uses LLMs and embeddings to process datasets with up to 1000x speedups
A high-performance 3D Gaussian Splatting rasterizer for rendering AI-generated graphics.
A fast and simple image labeling/annotation tool with support for multiple formats like COCO, PASCAL VOC, and more.
Get weekly updates on trending AI coding tools and projects.