Toolkit for optimising and running deep learning inference on Intel CPUs and integrated GPUs, including model conversion, quantisation and the runtime. Built and maintained by WIEWAVE for Azure Marketplace and AWS Marketplace, on Ubuntu, Debian, Red Hat Enterprise Linux, AlmaLinux and Rocky Linux.
| Built & maintained by | WIEWAVE |
|---|---|
| Category | AI & Machine Learning |
| Operating systems | Ubuntu, Debian, Red Hat Enterprise Linux, AlmaLinux, Rocky Linux |
| Marketplaces | Azure Marketplace and AWS Marketplace |
| Offer types | Public listing, with private offers on request |
| Marketplace | Status |
|---|---|
| Azure Marketplace | Published |
| AWS Marketplace | Published |
| Google Cloud Marketplace | Available on request |
Need it on another marketplace, or as a private offer for your organisation? cloud@wiewave.com
Each image follows its distribution's own provisioning model, package manager and security tooling — not one build relabelled several times.
LTS and interim releases, Minimal and Pro variants, built to Canonical's cloud-image conventions.
Stable and oldstable, with backports where a workload needs a newer runtime than the release ships.
RHEL 8 and 9 images, including BYOS and pay-as-you-go licensing models on each marketplace.
The 1:1 RHEL-compatible rebuild, and the default landing spot for teams migrating off CentOS Linux.
Enterprise-grade RHEL compatibility with a community governance model, on 8 and 9 streams.
The same four steps behind every offer we've published, including the hardening and CIS Benchmark checks every build goes through.
The distribution, licensing model and target marketplaces are agreed before anything is built.
Packer templates, Ansible provisioning and a pinned package set — then hardened, scanned and checked against the CIS Benchmark for its distribution.
Taken through each cloud's own certification pipeline before it goes live on the marketplace.
Rebuilt on the upstream security cadence and re-published, with old versions retired without breaking deployments.
If yours isn't here, ask our marketplace team directly.
GPU-ready training and inference images with drivers, CUDA and frameworks already matched to each other.
Stable Diffusion interface with a node-based canvas, inpainting, ControlNet support and model management, served as a web application on GPU instances.
NumPy-compatible Python library for autodiff and XLA-accelerated array computation, installed with the runtime needed for CPU or GPU numerical workloads.
Python framework for building multimodal and neural search services, exposing gRPC and HTTP endpoints for embedding pipelines and vector retrieval.
Just-in-time compiled deep learning framework using meta-operators and unified graph execution, installed with Python bindings for model training.
Python utilities for lightweight pipelining: transparent disk caching of function results, parallel loops and efficient persistence of large NumPy arrays.
Minimal Jupyter base environment from the official docker-stacks lineage, giving a conda-managed Python kernel to build custom notebook images on.
Tell us the distribution, the marketplace and the commercial model — we'll build, certify and publish it as a public listing or a private offer.
