Lists (1)
Starred repositories
OpenSandbox is a general-purpose sandbox platform for AI applications, offering multi-language SDKs, unified sandbox APIs, and Docker/Kubernetes runtimes for scenarios like Coding Agents, GUI Agent…
Rapid and cost-effective operator and best practice for agent sandbox lifecycle management.
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
Lightning-Fast RL for LLM Reasoning and Agents. Made Simple & Flexible.
A NCCL extension library, designed to efficiently offload GPU memory allocated by the NCCL communication library.
agent-sandbox enables easy management of isolated, stateful, singleton workloads, ideal for use cases like AI agent runtimes.
Container runtimes on macOS (and Linux) with minimal setup
Official PyTorch implementation for "Large Language Diffusion Models"
A workload for deploying LLM inference services on Kubernetes
A Datacenter Scale Distributed Inference Serving Framework
Unified Communication X (mailing list - https://elist.ornl.gov/mailman/listinfo/ucx-group)
Gateway API Inference Extension
Achieve state of the art inference performance with modern accelerators on Kubernetes
SGLang is a high-performance serving framework for large language models and multimodal models.
FlashMLA: Efficient Multi-head Latent Attention Kernels
Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation
Cost-efficient and pluggable Infrastructure components for GenAI inference
A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations
Hwameistor is an HA local storage system for cloud-native stateful workloads.
A multi-cluster batch queuing system for high-throughput workloads on Kubernetes.
A tool to list and diagnose Go processes currently running on your system
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.