MoonEP: A Perfectly Balanced Expert Parallelism Library via Dynamic Redundant Experts

A Library for Advanced Deep Time Series Models for General Time Series Analysis.

KVarN is a native vLLM KV-cache quantization backend for your agents: 3-5x more context, throughput above FP16, and FP16-level accuracy. Calibration-free, one flag.

A framework for efficient model inference with omni-modality models

Collection-LLM-RAG is a Retrieval-Augmented Generation (RAG) application designed to explore collections of web articles and PDF files, such as conference papers.

(ICLR 2024) GRANDE: Gradient-Based Decision Tree Ensembles

(ICLR 2024) GRANDE: Gradient-Based Decision Tree Ensembles

Serve, optimize and scale PyTorch models in production

Here I will try to implement the solution of PDEs using PINN on pytorch for educational purpose

This code uses the pyTorch Conv2D modules to make the PIV algorithms work faster on GPU

Implementing Machine Learning algorithms from scratch to gain in-depth understanding about the foundations on which the algorithms are built.

This comprehensive, hands-on course provides a thorough exploration into the world of algorithmic trading, aimed at students, professionals, and enthusiasts with a basic understanding of Python pro…

Orientation Analysis of Solar Panel

Scalable and Accurate Subsequence Transform

A scikit-learn compatible Python package for GPU-accelerated computation of the signature kernel using CuPy.

Code for my Master's Thesis

Seq2Tens: An efficient representation of sequences by low-rank tensor projections

A scikit-learn-compatible library for estimating prediction intervals and controlling risks, based on conformal predictions.

Make AI do actual work. Swap the model anytime — keep everything you've built.

Time-series machine learning at scale. Built with Polars for embarrassingly parallel feature extraction and forecasts on panel data.

We well know GANs for success in the realistic image generation. However, they can be applied in tabular data generation. We will review and examine some recent papers about tabular GANs in action.

Lightweight, useful implementation of conformal prediction on real data.

A comprehensive survey on the time series domains

A playbook for systematically maximizing the performance of deep learning models.

Source code for ClimateLearn

Scalene: a high-performance, high-precision CPU, GPU, and memory profiler for Python with AI-powered optimization proposals