Loonloon's repositories
ARMCL-pipe-all
CPU-GPU Layer-Switched Low Latency CNN Inference, 25th Euromicro Conference on Digital System Design (DSD), 2022
ChemAgents
A Multiagent-Driven Robotic AI Chemist Enabling Autonomous Chemical Research On Demand
CoDL
CoDL: Efficient CPU-GPU Co-execution for Deep Learning Inference on Mobile Devices
darknet-OpenCL-sowson
Darknet on OpenCL Convolutional Neural Networks on OpenCL on Intel & NVidia & AMD & Mali GPUs for macOS & GNU/Linux
DeepTrust-RT-2024
Code repo for DeepTrust-RT work
DeepVideoCS
PyTorch deep learning framework for video compressive sensing.
FAI-PEP
Facebook AI Performance Evaluation Platform
Fault-Tolerant-SGEMM-on-NVIDIA-GPUs
Anatomy of High-Performance GEMM with Online Fault Tolerance on GPUs, ICS 2023
graphene
Graphene / Graphene-SGX Library OS - a library OS for Linux multi-process applications, with Intel SGX support
GuaranTEE
Hamed Haddadi, GuaranTEE: Towards Attestable and Private ML with CCA, EuroMLSys 2024 (CCF-A)
Parallel_NMS
Parallel CUDA implementation of NON maximum Suppression
plinius
Plinius: Secure ML model training with Intel SGX and PM for fault tolerance
pmt
Power Measurement Tool
PowerInfer
High-speed Large Language Model Serving for Local Deployment
rockchip_mirrors-BSP
Mirrors of rockchip BSP repositories.
SmartZone
Memory-Efficient and Secure DNN Inference on TrustZone-enabled Consumer IoT Devices, InfoCOM 2024
TSC-VEE
TSC-VEE: A TrustZone-Based Smart Contract Virtual Execution Environment
UGFraud
An Unsupervised Graph-based Toolbox for Fraud Detection
vscode-opencl
OpenCL for Visual Studio Code