👕 An open-source course that will teach you how to build and deploy a real-time personalized recommender for H&M fashion articles.

A list of awesome papers and resources of recommender system on large language model (LLM).

LLM inference in C/C++

Model Context Protocol Servers

Scripts for fine-tuning Meta Llama with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting…

llama3 implementation one matrix multiplication at a time

Preventing Zero-Shot Transfer Degradation in Continual Learning of Vision-Language Models

GPU-accelerated Factors analysis library and Backtester

TorchQuantum is a backtesting framework that integrates the structure of PyTorch and WorldQuant's Operator for efficient quantitative financial analysis.

Analysis on systematic trading strategies (e.g., trend-following, carry and mean-reversion). The result is regularly updated.

Code for paper "Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapters" CVPR2024

Fast Differentiable Sorting and Ranking

Python program that rates stocks out of 100 based on valuation, profitability, growth, and price performance metrics, relative to the company's sector.

Coding a Multimodal (Vision) Language Model from scratch in PyTorch with full explanation: https://www.youtube.com/watch?v=vAmKB7iPkWw

A minimal implementation of vllm.

Making of cuda kernel

Official Pytorch implementation of "E2VPT: An Effective and Efficient Approach for Visual Prompt Tuning". (ICCV2023)

[CVPR 2023] Official repository of paper titled "MaPLe: Multi-modal Prompt Learning".

A lightweight library for portable low-level GPU computation using WebGPU.

🔎 📈 🐍 💰 Backtest trading strategies in Python.

PyTorch implementation of various methods for continual learning (XdG, EWC, SI, LwF, FROMP, DGR, BI-R, ER, A-GEM, iCaRL, Generative Classifier) in three different scenarios.

A Framework of Continual Learning

Python toolkit for quantitative finance

UNet diffusion model in pure CUDA

Notes on "Programming Massively Parallel Processors" by Hwu, Kirk, and Hajj (4th ed.)

Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformation (ICLR 2020 spotlight)

A python library to develop workflow based chatbots

The code repository for "Expandable Subspace Ensemble for Pre-Trained Model-Based Class-Incremental Learning"(CVPR24) in PyTorch.