Explore Projects
Discover 11 open source projects
Showing 1-11 of 11 projects
bigscience-workshop/petals
A distributed system for running large language models (LLMs) on personal devices, enabling faster fine-tuning and inference.
FMInference/FlexLLMGen
A Python library for running large language models on a single GPU for high-throughput scenarios.
katanemo/plano
Delivers infrastructure for agentic apps with AI-native proxy and data plane.
cloud-hypervisor/cloud-hypervisor
A secure, Rust-based Virtual Machine Monitor for modern cloud workloads with support for Windows and Linux guests.
alewin/useWorker
useWorker() is a React Hook that allows you to offload blocking tasks to a web worker for a more responsive UI.
dvmazur/mixtral-offloading
Run Mixtral-8x7B language models on Colab or consumer desktops with offloading capabilities.
pshihn/workly
A simple library to move a function or class to a web worker, enabling developers to offload CPU-intensive tasks.
NVIDIA/aistore
AIStore: A scalable, high-performance, and high-availability storage solution for AI applications and workloads.
developit/stockroom
A state management library that offloads store management to a web worker for improved performance.
apache/incubator-gluten
Gluten is a Scala library that offloads JVM-based SQL engines' execution to native engines for improved performance.
cdnbye/hlsjs-p2p-engine
A peer-to-peer CDN engine for HLS-based video streaming that uses WebRTC to offload traffic from the server.
Stay in the loop
Get weekly updates on trending AI coding tools and projects.