karhoutam Goto Github PK

cuda-kernels

Some common CUDA kernel implementations (Not the fastest).

federated-averaging-pytorch

Implementation of FedAvg

fedrecon

PyTorch Implementation of Federated Reconstruction: Partially Local Federated Learning

fl-bench

Benchmark of federated learning. Dedicated to the community. 🤗

flower

Flower: A Friendly Federated Learning Framework

karhoutam

llm.c

LLM training in simple, raw C/CUDA

per-fedavg

PyTorch Implementation of Personalized federated learning with theoretical guarantees: A model-agnostic meta-learning approach

personalized-fedavg

Implementation of Improving Federated Learning Personalization via Model Agnostic Meta Learning

pfedla

PyTorch implementation of Layer-wised Model Aggregation for Personalized Federated Learning

ray

Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

scaffold-pytorch

Implementation of SCAFFOLD: Stochastic Controlled Averaging for Federated Learning

test