[ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring

rocSHMEM intra-kernel networking runtime for AMD dGPUs on the ROCm platform.

[DEPRECATED] Moved to ROCm/rocm-libraries repo

Local-first AI Notepad for Private Meetings

AI app store powered by 24/7 desktop history. open source | 100% local | dev friendly | 24/7 screen, mic recording

mcp-use is the easiest way to interact with mcp servers with custom agents

OpenVINO Intel NPU Compiler

mysteries about Hardware in software engineer's eyes

This is a simple demonstration of more advanced, agentic patterns built on top of the Realtime API.

MiniCPM-V 4.5: A GPT-4o Level MLLM for Single Image, Multi Image and High-FPS Video Understanding on Your Phone

Using OpenVINO to speed up MeloTTS inference

Using OpenVINO to speed up moondream2 inference

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

🤗 Optimum Intel: Accelerate inference with Intel optimization tools

🤱🏻 Turn any webpage into a desktop app with one command. 一键打包网页生成轻量桌面应用

llm deploy project based mnn. This project has merged into MNN.

Triton backend that enables pre-process, post-processing and other logic to be implemented in Python.

NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.

BladeDISC is an end-to-end DynamIc Shape Compiler project for machine learning workloads.

OpenVINO™ is an open source toolkit for optimizing and deploying AI inference

Scalable and flexible workflow orchestration platform that seamlessly unifies data, ML and analytics stacks.

AutoKernel 是一个简单易用，低门槛的自动算子优化工具，提高深度学习算法部署效率。

The Triton backend for TensorRT.