hwu36

stable-diffusion-webui

Stable Diffusion web UI

pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

stablediffusion

High-Resolution Image Synthesis with Latent Diffusion Models

DeepSpeed

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

Paddle

PArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice （『飞桨』核心框架，深度学习&机器学习高性能单机、分布式训练和跨平台部署）

onnxruntime

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

MNN

MNN is a blazing fast, lightweight deep learning framework, battle-tested by business-critical use cases in Alibaba

xformers

Hackable and optimized Transformers building blocks, supporting a composable construction.

oneflow

OneFlow is a deep learning framework designed to be user-friendly, scalable and efficient.

cutlass

CUDA Templates for Linear Algebra Subroutines

AITemplate

AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.

spack

A flexible package manager that supports multiple versions, configurations, platforms, and compilers.

jittor

Jittor is a high-performance deep learning framework based on JIT compiling and meta-operators.

xla

A machine learning compiler for GPUs, CPUs, and ML accelerators

FlexFlow

FlexFlow Serve: Low-Latency, High-Performance LLM Serving

voltaML-fast-stable-diffusion

Beautiful and Easy to use Stable Diffusion WebUI

nnfusion

A flexible and efficient deep neural network (DNN) compiler that generates high-performance executable from a DNN model description.

BladeDISC

BladeDISC is an end-to-end DynamIc Shape Compiler project for machine learning workloads.

megablocks

hidet

An open-source efficient deep learning framework/compiler, written in python.

x-stable-diffusion

Real-time inference for Stable Diffusion - 0.88s latency. Covers AITemplate, nvFuser, TensorRT, FlashAttention. Join our Discord communty: https://discord.com/invite/TgHXuSJEk6

byteir

A model compilation solution for various hardware

raf

cutlass-kernels

gpuocelot

GPUOcelot: A dynamic compilation framework for PTX

SparTA

coconet

Cutlass_EX

study of cutlass

SPARTA

SParse AcceleRation on Tensor Architecture

SeRe

Code for project "NeRF4SeRe: Neural Radiance Fields for Scene Reconstruction". (2022-2023-1) AI3604@SJTU: Computer Vision.