aici

mttl

Building modular LMs with parameter-efficient fine-tuning.

tutel

Tutel MoE: An Optimized Mixture-of-Experts Implementation

promptflow-rag-project-template

An end-to-end sample of RAG showcasing development, evaluation, experimentation, and deployment u...

llguidance

Low-level Guidance Parser

PromptCraft-Robotics

Community for applying LLMs to robotics and a robot simulator with ChatGPT integration

torchscale

Foundation Architecture for (M)LLMs

evodiff

Generation of protein sequences and evolutionary alignments via discrete diffusion models

goodpoints

A Python package for generating concise, high-quality summaries of a probability distribution

DeepSpeed-MII

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

BioGPT

VRL3

BlingFire

A lightning fast Finite State machine and REgular expression manipulation library.

subseasonal_toolkit

Subseasonal forecasting models

MInference

To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention,...

cloud-advocate-workshops

Workshops created by the Cloud Advocacy team at Microsoft.