CUDA inference backend for Unsloth - Tesla T4 optimized with FlashAttention, Tensor Cores, and native Python API

GitHub Copilot CLI brings the power of Copilot coding agent directly to your terminal.

Gemini auth plugin for opencode

Agentic Ops Framework

2-2000x faster ML algos, 50% less memory usage, works on all hardware - new and old.

Streamlit Component for rendering Folium maps

An ensemble approach to accurately detect somatic mutations using SomaticSeq

LLMRouter: An Open-Source Library for LLM Routing

LM Studio CLI

Svelte Kit Tutorial with Remote Functions, Async, Drizzle, Better Auth

LM Studio TypeScript SDK

Intelligent textbook for a 15 week high-school physics course.

How to use AU and mkdocs material with education theory to create intelligent textbooks

NVIDIA curated collection of educational resources related to general purpose GPU programming.

Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.

A high-performance, asynchronous toolkit for building MCP servers and clients in Rust.

Lightweight C++ LLM agent framework

Unified Communication X (mailing list - https://elist.ornl.gov/mailman/listinfo/ucx-group)

Client application of the UXI Group Studies infrastructure for conducting user studies with eye tracking.

RDMA core userspace libraries and daemons

Lightning fast C++/CUDA neural network framework

NVIDIA Networking NIC Configuration Operator For Kubernetes

NVIDIA GPUDirect Storage Driver

An open source flash player implementation