Lists (5)
Stars
DeepInfer: High-performance, large-scale inference framework for DeepSeek models
2D and 3D cross-platform GPU multi-physics engine in Rust
Local inference that behaves like a frontier API: Qwen3.8-Flash-Next on AMD Strix Halo plus small NPU models, over the OpenAI and Anthropic APIs on one port.
[ICLR 2026] Code for QuantVGGT: Quantized Visual Geometry Grounded Transformer
Make videos on the computer you already own. FreeVideo runs MiniMax H3 in as little as 8 GB of VRAM and 16 GB of RAM, and adapts its acceleration path to your hardware.
Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.
Your Ryzen AI Max is running at half speed. SnowLLM: up to 9x faster prefill and 2x faster decode than llama.cpp on the same GGUF. Qwen3.6-35B-A3B, Qwen3.8-Flash-Next, DeepSeek-V4-Flash.
Orca lets you run a fleet of coding agents (e.g. Claude Code, Codex) with your own subscription. Available on desktop, mobile and remote runtime.
Fast and memory-efficient classical machine learning operators
Microduck 复刻：飞特 HD-1910 整机已实机验证（站立、行走、前滚翻起身）。镜像、Studio 网页中控、CAD/BOM、装配教程、电路工程与训练平台 | Microduck robot replica with real hardware demos.
FreeToken brings datacenter-scale model serving to your desktop. Run massive models locally, fast and efficiently.
The AI-Native Search Database. Best for agent storage, it unifies vector, text, structured, and semi-structured data into a single engine. This all-in-one database makes agents smarter, easier to r…
A framework for efficient model inference with omni-modality models
Keep AI coding agent CLIs from grinding down your SSD — relocate regenerable write targets to a RAM disk
momoten is an experimental translation and runtime layer that implements a restricted, buffer-oriented subset of the Vulkan compute API over OpenCL
nikki is an experimental translation and runtime layer that implements a restricted, buffer-oriented subset of the Vulkan compute API over WebGPU
Accessible large language models via k-bit quantization for PyTorch.
A Call of Duty-quality FPS in Three.js, built from a single prompt.
Palm on-device acceleration capabilities.
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
《深入理解 AI Agent：设计原理与工程实践》（李博杰 著）开源主仓库：全书正文、编译版 PDF 与按章配套代码
Hy3 (295B A21B), a leading reasoning and agent model in its size, with great cost efficiency.
DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms
AI 时代的伯克希尔：基于 Claude Code / Codex 的价值投资研究框架。巴菲特·芒格·段永平·李录四大师方法论 + 多Agent并行研究。| AI-era Berkshire: a value investing research framework built for Claude Code / Codex. 4 masters' methodologies + multi…
DFlash: Block Diffusion for Flash Speculative Decoding