Serve Generative AI models and answer prompts from European end-consumers securely.
What makes inference fast? Model optimization is one lever. To be served fast, a model must be optimized to the machines that run it.
This isn't always a piece of cake, and can turn into a time-consuming process. That's why Scaleway is providing an evolutionary Model Library, with curated and optimized LLMs.
Thanks to a complete GPU portfolio, the Managed Inference product is powered by the GPU you see fit: L4, H100 PCIe GPU Instances and very soon L40S GPU Instances. Multiple options to offer you the flexibility you need to reach efficiency and cost-effectiveness at the same time.
Enjoy tailored security for your infrastructure: from highly secure VPC environments to accessible setups with internet and IAM tokens.
Maintain complete data control: no storage nor third-party access to your data (prompt & responses), ensuring it remains exclusively yours and within Europe.
Available zones:
Paris:PAR 2Trained on Scaleway's Nabuchodonosor 2023, Mixtral-8x7B is a state-of-the-art, pretrained generative model known as a Sparse Mixture of Experts. It has been benchmarked to surpass the performance of the Llama 2 70B model across a variety of tests.
Llama 3 by Meta is the latest iteration of the open-access Llama family, for efficient deployment and development on smaller GPUs. Llama models are tailored for dynamic dialogues and creative text generation. Engineered with the latest in efficiency and scalability, it excels in complex reasoning and coding tasks. Its advanced Grouped-Query Attention mechanism ensures unparalleled processing prowess, making it the ultimate tool for chat applications and beyond.
A cutting-edge language model boasting 70 billion parameters, crafted with the innovative Evol+ approach for unparalleled response quality. With its extensive training on a diverse dataset and a 4k context window, it's engineered to excel in understanding and generating complex instructions, positioning it as a leader in natural language processing capabilities.
Your AI endpoints are accessible through low-latency and secure connection to your resources hosted at Scaleway, thanks to a resilient regional Private Network.
We make generative AI endpoints compatible with Scaleway's Identity and Access Management, so that your deployments are compliant with your enterprise architecture requirements.
Identify bottlenecks on your deployments, view inference requests in real time and even report your energy consumption with a fully managed observability solution.
