JAX-accelerated time-series forecasting library. Fast, scalable, and NumPy-compatible.

Linear solvers in JAX and Equinox. https://docs.kidger.site/lineax

This repository contains the official implementation of the paper: Goal-Oriented Time-Series Forecasting: Foundation Framework Design

Time-Series-Optimized Transformer for Observability

Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/

Zero-shot Time Series Forecasting with TabPFN (work accepted at NeurIPS 2024 TRL and TSALM workshops)

⚡ TabPFN: Foundation Model for Tabular Data ⚡

ProbTS is a benchmarking toolkit for time series forecasting.

Context is Key: A Benchmark for Forecasting with Essential Textual Information

Codebase for Aria - an Open Multimodal Native MoE

LLM101n: Let's build a Storyteller

Megatron's multi-modal data loader

Gradient Boosting Reinforcement Learning (GBRL)

Just a pet project.

Modern Fixed Point Systems using Pytorch

MOMENT: A Family of Open Time-series Foundation Models, ICML'24

TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.

[PVLDB 2024 Best Paper Nomination] TFB: Towards Comprehensive and Fair Benchmarking of Time Series Forecasting Methods

HPT - Open Multimodal LLMs from HyperGAI

Puzzles for learning Triton

Development repository for the Triton language and compiler

Chronos: Pretrained Models for Time Series Forecasting

Type annotations and runtime checking for shape and dtype of JAX/NumPy/PyTorch/etc. arrays. https://docs.kidger.site/jaxtyping/