A primitive library for neural network

LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.

Universal LLM Deployment Engine with ML Compilation

A high-throughput and memory-efficient inference and serving engine for LLMs

for cuda training lib

Common libraries for PPL projects

A method to increase the speed and lower the memory footprint of existing vision transformers.

CMake configurations for PPL projects

PPL Quantization Tool (PPQ) is a powerful offline neural network quantization tool.

ppl.cv is a high-performance image processing library of openPPL supporting various platforms.

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

High-speed simulator of convolutional spiking neural networks with at most one spike per neuron.

Speed up Stable Diffusion with this one simple trick!

Tensorflow Faster R-CNN for Windows and Python 3.5

Voice data <= 10 mins can also be used to train a good VC model!

ncnn is a high-performance neural network inference framework optimized for the mobile platform

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

High-Resolution Image Synthesis with Latent Diffusion Models

A CPU tool for benchmarking the peak of floating points

Chinese MapleStory Server Ver.143

Official Tensorflow implementation of Ev-SegNet