Introduction A few weeks ago, the release of the open-source large language model DeepSeek-R1 has taken the AI world by storm. The Chinese research team claimed their new reasoning model was on par with OpenAI’s flagship model o1, open-sourced the model and gave details about the work behind it. In this blog post series, we […]
Deep Dive into DeepSeek-R1 – Part 1 Read More »
OVHcloud strives for openness, expert takes and customer centricity. As part of this commitment, we keep adapting to next-gen industry shifts. Our goal remains the same: to provide our community with top market solutions. Up to now, OVHcloud had offered a Managed Caching service based on the renowned Redis engine. We helped our customers to
Managed Valkey: Our Commitment to Open Source and Customer choice. Read More »
You are not dreaming! You can deploy open-source LLM in a single command line. Deploying advanced language models can be a challenge! But this sometimes this arduous task is becoming increasingly accessible, enabling developers to integrate sophisticated AI capabilities into their applications. In this guide, we will walk through deploying the Mistral-Small-24B-Instruct-2501 model using vLLM
Several month ago we discovered Falco, a Cloud Native near real-time threats detection tool, and we saw how to install it on an OVHcloud MKS cluster. Today we will connect our Falco instance to a MKS cluster in order to retrieve Kubernetes Audit Logs events and watch if everything is OK in our cluster. Concretely,
On March 29th, Andres Freund, a Postgres developer, working at Microsoft, identified a response time while authenticating to openSSH on a Debian Sid installation that was about 500 ms longer as usual. He investigated the behaviour and concluded that liblzma, part of the xz library, was compromised by a complex backdoor injected into distribution packages
Backdoor in xz/liblzma (CVE-2024-3094) Read More »
During October, 2023, the Hacktober Fest is taking place. What is Hacktober Fest? Hacktoberfest is DigitalOcean’s annual event that encourages people to contribute to open source throughout October. It’s a way to highlight open source projects with boosting the participation of resolving issues by reward the committers. You have to fix at list 4 issues
OVHcloud and Hacktober Fest 2023 Read More »
Here @OVHCloud, we try to replace our legacy metrics oriented infrastructure. This infrastructure matters a lot for us as internal teams use it to supervise the core services of OVH, so before making any choices, we wanted to apply a bullet proof test to the challengers. You can do two main things with a storage
Benchmarking Prometheus promql performance Read More »
At OVHcloud, we recently made a change to our internal Observability stack. After testing and comparing the different solutions on the market, we opted for on open source solution. With this blog post, we’re starting a series of articles to provide feedback on our selection process and what we’ve learned along the way. Our mission
Welcome to Prometheus world of remote storage Read More »
A guide to deploy a custom Docker image for a Streamlit app with AI Deploy. Welcome to the second article concerning custom Docker image deployment. If you haven’t read the previous one, you can read it on the following link. It was about Gradio and sketch recognition. When creating code for a Data Science project,
A guide to deploy a custom Docker image for a Gradio app with AI Deploy. When creating code for a Data Science project, you probably want it to be as portable as possible. In other words, it can be run as many times as you like, even on different machines. Unfortunately, it is often the
