hyfrey

kueue

Kubernetes-native Job Queueing

outlines

Structured Text Generation

treelite

Universal model exchange and serialization format for decision tree forests

rapids-triton

fil_backend

FIL backend for the Triton Inference Server

MLServer

An inference server for your machine learning models, including support for multiple frameworks, multi-model serving and more

hey

HTTP load generator, ApacheBench (ab) replacement

distilabel

⚗️ distilabel is a framework for synthetic data and AI feedback for AI engineers that require high-quality outputs, full data ownership, and overall efficiency.

whisper.cpp

Port of OpenAI's Whisper model in C/C++

langchain

🦜🔗 Build context-aware reasoning applications

ollama

Get up and running with Llama 3.1, Mistral, Gemma 2, and other large language models.

gjson

Get JSON values quickly - JSON parser for Go

feathr

Feathr – A scalable, unified data and AI engineering platform for enterprise

DeepCTR-Torch

【PyTorch】Easy-to-use,Modular and Extendible package of deep-learning based CTR models.

DeepCTR

Easy-to-use,Modular and Extendible package of deep-learning based CTR models .

peft

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

or-tools

Google's Operations Research tools:

volcano

A Cloud Native Batch System (Project under CNCF)

gluonts

Probabilistic time series modeling in Python

laktory

A DataOps framework for building a lakehouse.

dill

serialize all of Python

kornia

Geometric Computer Vision Library for Spatial AI

iree

A retargetable MLIR-based machine learning compiler and runtime toolkit.

onnx-mlir

Representation and Reference Lowering of ONNX Models in MLIR Compiler Infrastructure

llvmlite

A lightweight LLVM python binding for writing JIT compilers

llvm-project

The LLVM Project is a collection of modular and reusable compiler and toolchain technologies.

docker-clang

Dockerfiles for Clang and LLVM

LWM

magika

Detect file content types with deep learning

minbpe

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.