MaximeRobeyns

squared-npcs

Squared Non-monotonic Probabilistic Circuits

posteriors

Uncertainty quantification with PyTorch

hatchet

A distributed, fault-tolerant task queue

wedges

An ever-expanding, open-source React UI library built with the Wedges Design System, Radix primitives, and Tailwind CSS.

auto_builder

Derive safe builders for rust structs

ColBERT

ColBERT: state-of-the-art neural search (SIGIR'20, TACL'21, NeurIPS'21, NAACL'22, CIKM'22, ACL'23, EMNLP'23)

open-tts-tracker

resource-stream

CUDA related news and material links

nlm-ingestor

This repo provides the server side code for llmsherpa API to connect. It includes parsers for various file formats.

timescaledb

An open-source time-series SQL database optimized for fast ingest and complex queries. Packaged as a PostgreSQL extension.

surya

OCR, layout analysis, reading order, line detection in 90+ languages

polars

Dataframes powered by a multithreaded, vectorized query engine, written in Rust

all-in-one

📦 The official Nextcloud installation method. Provides easy deployment and maintenance with most features included in this one Nextcloud instance.

ui

Beautifully designed components that you can copy and paste into your apps. Accessible. Customizable. Open Source.

gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

StyleTTS2

StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models

shuttle

Build & ship backends without writing any infrastructure files.

30-day-map-challenge

Maps made as part of the #30DayMapChallenge - mostly in python but also use QGIS and other tools

PiPPy

Pipeline Parallelism for PyTorch

voyager

🛰️ An approximate nearest-neighbor search library for Python and Java with a focus on ease of use, simplicity, and deployability.

SlimTrainer

Full finetuning of large language models without large memory requirements

llm-awq

[MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

gvisor

Application Kernel for Containers

tokenmonster

Ungreedy subword tokenizer and vocabulary trainer for Python, Go & Javascript

orbit

A Python package for Bayesian forecasting with object-oriented design and probabilistic models under the hood.

exllamav2

A fast inference library for running LLMs locally on modern consumer-class GPUs

nanoT5

Fast & Simple repository for pre-training and fine-tuning T5-style models

autogluon

Fast and Accurate ML in 3 Lines of Code

outlines

Structured Text Generation

statsforecast

Lightning ⚡️ fast forecasting with statistical and econometric models.