-
EPFL
- Lausanne
- https://rishisharma.netlify.app
Highlights
- Pro
Stars
Naptha is a framework and infrastructure for developing and running multi-agent systems at scale with heterogeneous models, architectures and data
Source code for our paper "Fair Decentralized Learning" in SaTML 2025.
Material workbench for the master-level course CS-E4740 "Federated Learning"
Code for visualizing the loss landscape of neural nets
P2PFL is a decentralized federated learning library that enables federated learning on peer-to-peer networks using gossip protocols, making collaborative AI model training possible without reliance…
Source code for our paper "Boosting Asynchronous Decentralized Learning with Model Fragmentation" in ACM WWW 2025.
SkyPilot: Run AI and batch jobs on any infra (Kubernetes or 14+ clouds). Get unified execution, cost savings, and high GPU availability via a simple interface.
Releasing the spot availability traces used in "Can't Be Late" paper.
An Open Framework for Federated Learning.
prime is a framework for efficient, globally distributed training of AI models over the internet.
Disaggregated serving system for Large Language Models (LLMs).
High performance Transformer implementation in C++.
The Benchmark of Data Heterogeneity Evaluation Approaches
A simulator for Decentralized Learning algorithms, based on discrete-event simulation
Contains the source code of our Middleware'24 paper "QuickDrop: Efficient Federated Unlearning via Synthetic Data Generation"
SONAR - Self-Organizing Network of Aggregated Representations
Source code to support the paper "Noiseless Privacy Preserving Decentralized Learning" at PoPETS 2025.
Friends don't let friends make certain types of data visualization - What are they and why are they bad.
Curated collection of papers in machine learning systems
A simplified library for decentralized, privacy preserving machine learning
An awesome list of papers on privacy attacks against machine learning
A curated list of Meachine learning Security & Privacy papers published in security top-4 conferences (IEEE S&P, ACM CCS, USENIX Security and NDSS).
Perform data science on data that remains in someone else's server
Curated list of project-based tutorials
Building blocks for foundation models.