Heterogeneous GPU Sharing on Kubernetes

GPT Image 2 prompt gallery, image prompt library, agentic skill, and CLI for OpenAI image generation/editing

You like pytorch? You like micrograd? You love tinygrad! ❤️

Everything we actually know about the Apple Neural Engine (ANE)

Training neural networks on Apple Neural Engine via reverse-engineered private APIs

The LLVM Project is a collection of modular and reusable compiler and toolchain technologies.

Awesome LLM compression research papers and tools.

Memory library for building stateful agents

real time face swap and one-click video deepfake with only a single image

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1

LLM KV cache compression made easy

Official Implementation for [ICLR26] DefensiveKV: Taming the Fragility of KV Cache Eviction in LLM Inference

hexagon tutorial

LLM inference in C/C++

FastRPC is Qualcomm's userspace library that facilitates efficient remote procedure calls between the CPU and DSP for high-performance computing.

AIOS: AI Agent Operating System

Spec-driven development (SDD) for AI coding assistants.

Awesome resources for GPUs

MobileFineTuner: Native C++ framework for fine-tuning LLMs directly on mobile devices. Features: LoRA/Full-FT, ZeRO-inspired parameter sharding, energy-aware throttling, custom autograd engine. Kee…

[ICLR 2025] Official implementation of MS-Diffusion: Multi-subject Zero-shot Image Personalization with Layout Guidance

Using AI for high quality writing

一款简单易用和高性能的AI部署框架 | An Easy-to-Use and High-Performance AI Deployment Framework