# nod-ai/AMD-SHARK-Studio

AMD-SHARK Studio -- Web UI for SHARK+IREE High Performance Machine Learning Distribution

Repository: https://github.com/nod-ai/AMD-SHARK-Studio
Canonical: https://ross.abutalabs.com/products/amd-shark-studio
Language: Python
License: Apache-2.0
License Family: permissive
Topics: deep-learning, machine-learning, mlir, pytorch, amd, apple-silicon, nvidia
Last push: 2025-12-15T05:40:50+00:00

## Health v2 (maintenance only)
Score: 48/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 57, release rhythm 8, longevity 100
- inputs: {"age_days": 1643, "days_push": 261, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1451, forks 166 (observed 2026-08-28T04:04:46.039404+00:00)

## What it is
AMD-SHARK Studio is a web UI distribution for high-performance machine learning inference built on SHARK and IREE, primarily for running Stable Diffusion models on AMD, NVIDIA, and Apple Silicon GPUs via Vulkan. The project is explicitly not currently maintained.

## Use cases
- run stable diffusion locally on an AMD GPU
- generate images with a local web UI on Windows
- run ML models with Vulkan on Apple Silicon
- high performance stable diffusion inference without CUDA
- download an exe and start generating images locally

## When to choose
- you have an AMD RDNA GPU and want local Stable Diffusion on Windows
- you want a simple one-click installer for GPU-accelerated image generation
- you specifically need the IREE/MLIR compiler stack for inference

## When to avoid
- you need an actively maintained project with bug fixes
- you want the broadest model and feature support like ComfyUI or A1111
- you rely on Linux MESA/RADV drivers or newer Vulkan SDKs on macOS

## Facets
- artifact type: application
- maturity: abandoned
- function: machine-learning, llm-inference, stable-diffusion, gpu-computing, gui
- domain: machine-learning, deep-learning, image-processing, gpu-computing
- platform: windows, python
- tags: iree, mlir, vulkan, stable-diffusion-ui, amd-gpu, not-maintained, macos, linux

## Member repositories
- nod-ai/AMD-SHARK-Studio (main) score 48

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:46.039404+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:35:52.053884+00:00, confidence not recorded.
  - readme: https://github.com/nod-ai/AMD-SHARK-Studio (fetched 2026-08-28T04:04:46.039404+00:00, sha 729726e9c233)
- Data as of 2026-08-30T08:39:29.467469+00:00.