rocm

project-maya

+656

Project Maya - run GLM-5.3-Flash (321B MoE) privately on your own GPU(s), from one card to 16, NVIDIA or AMD, Linux or Windows. Engine, server, dashboard, OpenAI- and Anthropic-compatible API, quant tools.

LMCache

+110

LMCache: Supercharge Your LLM with the Fastest KV Cache Layer

halogen-flash-server

+76

The fastest way to run Qwen3.8-Flash-Next on Strix Halo (gfx1151)

lemonade

+59

Lemonade helps users discover and run local AI apps by serving optimized LLMs right from their own GPUs and NPUs. Join our discord: https://discord.gg/5xXzkMu8Zk

InferenceX

+36

Open Source AI Accelerator Research Platform Standard / 开源推理研究平台

tracel-ai/burn

+32

Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.

gpustack

+31

A GPU cluster manager for high-performance AI model serving (vLLM, SGLang) and on-demand SSH-accessible GPU instances.

d4r

+21

NVIDIA's official DLSS 3/4/4.5 on AMD RDNA3/4 GPUs on Windows and Linux.

apache/tvm

+20

Open Machine Learning Compiler Framework