Stars
Information hub for our project training the largest possible historical LLMs.
This is an official implementation of "ModernTCN: A Modern Pure Convolution Structure for General Time Series Analysis" (ICLR 2024 Spotlight), https://openreview.net/forum?id=vpJMJerXHU
🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"
FlashMLA: Efficient Multi-head Latent Attention Kernels
A python package for FITS input/output wrapping cfitsio
A React-based UI toolkit for the web
Collection of community-built applications and projects leveraging Palantir's AIP Platform.
The world's best AI personal assistant for email. Open source app to help you reach inbox zero fast.
Don't just regulate gradients like in Muon, regulate the weights too
Flash-Muon: An Efficient Implementation of Muon Optimizer
SysEng-approved LSST throughput information
MacOS menu bar todo app built with Electron, React and Redux. It goals is to help you do deep work.
A community-supported supercharged document management system: scan, index and archive all your documents
NVIDIA Data Center GPU Manager (DCGM) is a project for gathering telemetry and measuring the health of NVIDIA GPUs
OpenTSLM: Time-Series Language Models for Reasoning over Multivariate Medical Text- and Time-Series Data
Multivariate time series forecasting
Figure sizes, font sizes, fonts, and more configurations at minimal overhead. Fix your journal papers, conference proceedings, and other scientific publications.
Matplotlib styles for scientific plotting
A Fair and Scalable Time Series Forecasting Benchmark and Toolkit.
Pytorch implementation of NIPS'23 paper: Adaptive Normalization for Non-stationary Time Series Forecasting: A Temporal Slice Perspective
Modular Multi-Agent System for Scientific Research Assistance