quantization-efficient-network

A header-only neural network library for microcontrollers, with partial bare-metal & native-os support.

FrostNet: Towards Quantization-Aware Network Architecture Search

Trustworthy onboard satellite AI in PyTorch→ONNX→INT8 with calibration, telemetry, and a PhiSat-2 EO tile-filter demo.

🚀 Leveraging advanced RNN with LSTM for efficient, real-time anomaly detection in IoT networks, optimized for performance in resource-constrained environments.

Learning Path: RISC-V & Advanced Edge AI on SiFive FE310-G002 SoC | 32-bit RISC-V | 320 MHz | 16KB L1 Instruction Cache | 128Mbit (16MB) QSPI Flash | 4-stage pipeline

eve-mli: making learning interesting

Clean C language version of quantizing llama2 model and running quantized llama2 model

Code for ICCV2025 paper 'Semantic Alignment and Reinforcement for Data-Free Quantization of Vision Transformers'

Learning Path: RISC-V & Advanced Edge AI on SiFive FE310-G002 SoC | 32-bit RISC-V | 320 MHz | 16KB L1 Instruction Cache | 128Mbit (16MB) QSPI Flash | 4-stage pipeline

I'm writing a white paper to help me successfully complete the "Architecture and Platform for Artificial Intelligence" exam for my master's degree. Stay tuned for updates!

This project demonstrates the impact of model design choices on both energy consumption and economic cost. It analyzes the weight importance within a neural network, estimates the total FLOPs required for inference, and explores how quantization and pruning affect resource efficiency.

A Tutorial Notebook to Quantization in Machine Learning

Official repo fpr research work: Evaluating Vision Encoder Quantization for Edge-Cloud VLMs: Where Evaluation Breaks When Moving from Development to Deployment