Flash Attention Minimal
A minimal implementation of Flash Attention 1 & 2 in just ~350 lines of CUDA code.
Machine Learning
Retrieval Augmented Structured Generation: Business Document Information Extraction As Tool Use
[IEEE 7th International Conference on Multimedia Information Processing and Retrieval (MIPR) 2024] This paper presents Retrieval Augmented Structured Generation (RASG), a novel general framework for Business Document Information Extraction that achieves state of the art (SOTA) results on both Key-Information Extraction (KIE) and Line Items Recognition (LIR).
Llama.cpp
A C++ implementation of Meta’s Llama2 generative large-language model. I also optimized the original C implementation by Karpathy by adding parallelization on the multi-head attention layer.
Expedock Assistant: ChatGPT Applied to Logistics Data
Expedock Assistant is a chatbot that allows you to ask questions about your shipments and get answers in real time. It’s like having a personal assistant that knows everything about your business, shipments and industry.
Expedock AutoML
Expedock’s AutoML Library – fit a model, run batch inference, and get explanations in one line of code each.
Booking Demand Prediction for Grab SEA
Booking demand prediction for Grab’s Southeast Asia operations. The project involves spatio-temporal forecasting, anomaly detection, and econometric modeling.