Positional Encoding Methods: Implementation Report
A deep-dive into 5 positional encoding strategies with mathematical formulations, code walkthroughs, architectural diagrams, and comparative analysis
Read more →Writing about research
Research notes on efficient AI, hardware, and the systems behind them.
4 articles about research
Newest first
Intro to Triton with Matrix Multiplication
Introduction to GPU programming with Triton and build the matrix multiplication along the way
Read more →
Quantization Aware Training Implementation Guide
Implementation details and best practices for Quantization Aware Training (QAT) with LoRA, including GPU memory optimization strategies
Read more →
Quantization Strategy Report: Switchable and Cyclic Precision Training
Comprehensive report on quantization strategies including switchable precision and cyclic precision training applied to WikiText-103 dataset
Read more →