hip

halogen-flash-server

+76

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

d4r

+21

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

ramalama

+8

RamaLama is an open-source developer tool that simplifies the local serving of AI models from any source and facilitates their use for inference in production, all through the familiar language of containers.

llama-cpp-rdna-boosts

+7

A set of performant RDNA/HIP patches against llama.cpp focusing on high speed inferencing with numerics assurance

CUDA-for-AMD-Windows

+5

Run CUDA-targeted Windows applications on AMD GPUs with ZLUDA + ROCm/HIP.

ROCm/hip

+5

HIP: C++ Heterogeneous-Compute Interface for Portability

halogen-server

+5

The fastest way to run Qwen3.8 27B on Strix Halo (gfx1151)