TurboDiffusion: 100–200× Acceleration for Video Diffusion Models
PiKV: KV Cache Management System for Mixture of Experts [Efficient ML System]
A Serving System for Distributed and Parallel LLM Quantization [Efficient ML System]
MobileFineTuner: Native C++ framework for fine-tuning LLMs directly on mobile devices. Features: LoRA/Full-FT, ZeRO-inspired parameter sharding, energy-aware throttling, custom autograd engine. Keep your data on-device.
160+ pages of handwritten notes from Stanford CS336: Language Modeling from Scratch, covering language modeling, LLM systems, and full-stack AI engineering from data to deployment and evaluation and RL alignment
End-to-end ML system to predict student academic risk with LightGBM, SHAP explainability, and Streamlit deployment
GPU-accelerated, fault-tolerant Schlieren/PIV shock tracking with interactive ROI, 1-px edges, and resumable training.
ML-powered system that predicts commit risk in real time and dynamically optimizes CI/CD testing using intelligent risk scoring.
Machine Learning Systems - MLSystems.dev
To associate your repository with the mlsystem topic, visit your repo's landing page and select "manage topics."