A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, or debugging agent systems that require e…

Awesome LLM compression research papers and tools.

This is originally a collection of papers on neural network accelerators. Now it's more like my selection of research on deep learning and computer architecture.

A simple and effective LLM pruning approach.

Code for the ICML 2023 paper "SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot".

Berkeley's Spatial Array Generator

성균관대학교 소프트웨어학과 졸업작품