A high-throughput and memory-efficient inference and serving engine for LLMs

Open deep learning compiler stack for cpu, gpu and specialized accelerators

NumPy & SciPy for GPU

Supercharge Your LLM with the Fastest KV Cache Layer

Simple, scalable AI model deployment on GPU clusters

Stable Diffusion web UI

A deep learning package for many-body potential energy representation and molecular dynamics

The most powerful and modular stable diffusion GUI, api and backend with a graph/nodes interface. Now ZLUDA enhanced for better AMD GPU performance.

Self-host the powerful Chatterbox TTS model. This server offers a user-friendly Web UI, flexible API endpoints (incl. OpenAI compatible), predefined voices, voice cloning, and large audiobook-scale text processing. Runs accelerated on NVIDIA (CUDA), AMD (ROCm), and CPU.

Tensors and Dynamic neural networks in Python with strong GPU acceleration

vLLM: A high-throughput and memory-efficient inference and serving engine for LLMs

Set up inference profiling in 60 seconds

Simple monkeypatch to boost AMD Navi 3 GPUs

Complete Guide how to run Pytorch with AMD rx460,470,480 (gfx803) GPUs

Horizon chart for CPU/GPU/Neural Engine utilization monitoring. Supports Apple M1-M4, Nvidia GPUs, AMD GPUs

Example on how to use pytorch/yolov8 object detection on computers with AMD integrated GPUs

ROCm Install Utilities: rocminstall.py script to install a specific ROCm release version/revision.

HIP backend patch for Numba, the NumPy aware dynamic Python compiler using LLVM.

AMD RAD's experimental RMA library for Triton.

Python Interface to HIP and hiprtc Library