writing really fast kernels

This is a list of useful libraries and resources for CUDA development.

Fast SAM 3D Body: Accelerating SAM 3D Body for Real-Time Full-Body Human Mesh Recovery

Faster Green Screen Keys — async multi-GPU inference engine for professional VFX pipelines

Speak Friend and Enter

pprofile + matplotlib = Python program profiled as an awesome heatmap!

A powerful set of Python debugging tools, based on PySnooper

Comprehensive GPU specifications database with 2,824 GPUs across NVIDIA, AMD, and Intel

Adobe's reference implementation of the OpenPBR BSDF

Tangle is a web app that allows the users to build and run Machine Learning pipelines without having to set up development environment.

This is a series of GPU optimization topics. Here we will introduce how to optimize the CUDA kernel in detail. I will introduce several basic kernel optimizations, including: elementwise, reduce, s…

[CVPR 2023] DepGraph: Towards Any Structural Pruning; LLMs, Vision Foundation Models, etc.

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.

Example models using DeepSpeed

MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

Simple real time visualisation of the execution of a Python program.

A list of papers, docs, codes about model quantization. This repo is aimed to provide the info for model quantization research, we are continuously improving the project. Welcome to PR the works (p…

[ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

[ICLR2025] Accelerating Diffusion Transformers with Token-wise Feature Caching

AI agents running research on single-GPU nanochat training automatically

SD.Next Quantization Engine

Courses on building, compressing, evaluating, and deploying efficient AI models.

Unbearably fast near-real-time pure-Python runtime-static type-checker.

Pruna is a model optimization framework built for developers, enabling you to deliver faster, more efficient models with minimal overhead.

Official Repository of the paper "Trajectory Consistency Distillation"