mlc

Social and customizable AI writing assistant! ✍️

DISCONTINUED (July 2025): the maintenance for this repository has been discontinued. Please refer to: https://github.com/STMicroelectronics/st-mems-machine-learning-core/ for the up-to-date tutorials, examples and tools for the Machine Learning Core (MLC) feature available in STMicroelectronics MEMS sensors.

Structured inference with Llama 2 in your browser

Examples, tutorials, and tools for the MLC, a dedicated core for machine learning processing embedded in STMicroelectronics MEMS sensors.

[ECCV'24] Self-training Room Layout Estimation via Geometry-aware Ray-casting

This project has implemented the RAG function on Jetson and supports TXT and PDF document formats. It uses MLC for 4-bit quantization of the Llama2-7b model, utilizes ChromaDB as the vector database, and connects these features with Llama_Index. I hope you like this project.

Realtime exchange rates of CUP and MLC ratio

A collapsed-cone convolution radiotherapy dose calculation algorithm

《机器学习编译》的学习笔记和练习代码

Varian ESAPI script that plots doserate vs gantry angle for VMAT plans

The proposed method captures local and global correlations using Low Rank label subspace transformation for Multi-label learning with Missing Labels (LRMML). The model considers an auxiliary label matrix which facilitates the missing label information recovery.

TVM MLIR interface

A React Native application that enables on-device Large Language Model (LLM) chat functionality with intelligent context management. Built with TypeScript and modern React Native practices.

Python-based tool for Quality Assurance of Varian TrueBeam MLCs

Browser-based AI assistant that runs entirely on your device without requiring an internet connection (after initial model download)

Browser-native local LLM benchmark/chat/compare toolkit for WebLLM models.

Reproducible ctx8192 compile and validation workflow for Qwen2.5-1.5B on MLC/WebLLM.

Solutions to the Machine Learning Compilation (MLC, mlc.ai) course exercises — TensorIR tensor programs, end-to-end model compilation, automatic program optimization, and framework integration with Apache TVM

Universal LLM Deployment Engine with ML Compilation