An agent for CUDA compute-communication kernel co-design

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

Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training

Semantic cache for LLMs. Fully integrated with LangChain and llama_index.

Measure and optimize the energy consumption of your AI applications!

An SSH command runner with a focus on simplicity

FriendliAI Model Hub

[NeurIPS 2022] A Fast Post-Training Pruning Framework for Transformers

Python packaging and dependency management made easy

A shell for research papers

Multi-DNN Inference Engine for Heterogeneous Mobile Processors

Dotfile management with bare git

Lightweight and Parallel Deep Learning Framework

Visualizer for neural network, deep learning and machine learning models

Official Matplotlib cheat sheets

Parses, and hovers math formula of c mathematical library functions