NVIDIA recently posted a security bulletin that illustrates several critical vulnerabilities found with NVIDIA drivers. Here is a basic summary of the key points: Affected Components NVIDIA GPU Display Driver: Vulnerabilities affect both Windows and Linux versions. CVE-2024-0117, CVE-2024-0118, CVE-2024-0119, CVE-2024-0120, CVE-2024-0121: These vulnerabilities in the user mode layer of the Windows driver allow an […]
Author Archives: Massed Compute
If you are building a service that relies on LLM inference performance, you want to know how to get the most tokens per second. There are various factors that can go into finding the right configuration to maximize your tokens per second throughput. With the recent release of NVIDIA drivers v560 and some updated version […]
Want to Build a Custom Chat GPT? Here’s How to Pick the Best Cloud Computing Platform If you’ve experimented with AI tools like Chat GPT, you already know how powerful Generative AI (GenAI) can be in enhancing your work. Whether you’re creating content, analyzing data, or improving workflows, you may be thinking: “Can I build […]
Hacktoberfest is an annual event that runs throughout October, celebrating open-source projects and the community of contributors who make them possible. For the 10th consecutive year, DigitalOcean is hosting Hacktoberfest, offering a welcoming environment for developers, especially those who are just beginning their journey into open source. It’s the perfect time to dive into contributing, […]
When it comes to Artificial Intelligence (AI) models, there are two key processes that allow it to generate outputs and or perform predictions: AI training and AI inference. Below we cover some common questions about the two. What is AI training? In the AI training phase of a machine learning model’s life cycle, you typically […]
While it may seem that AI is a recent phenomenon, the field of artificial intelligence has been developing for decades. However, now we’re seeing (and using) AI that can help us dramatically with our day-to-day tasks. What recent advancement caused this boom in AI technology? The answer is generative AI. What is generative AI? As […]
Artificial Intelligence (AI) development has become a cornerstone of innovation across numerous industries, from healthcare to finance, automotive to entertainment. As AI models grow more complex, the computational demands increase exponentially. To meet these demands, developers require powerful hardware to handle the intensive tasks associated with AI development. Cloud GPUs Graphics Processing Units) have emerged […]
Figure: Generated from our Art VM Image using Invoke AI Previously we performed some benchmarks on Llama 3 across various GPU types. We are returning again to perform the same tests on the new Llama 3.1 LLM. On July 23, 2024, the AI community welcomed the release of Llama 3.1 405B, 70B and 8B models. […]
What’s a great piece of advice when you venture on a creative path that requires efficiency? Don’t reinvent the wheel. In a nutshell, that’s model merging. Model merging in the context of AI is the practice of taking existing AI models, including Large Language Models (LLMs), and using them to create your own. Like in […]
NVIDIA’s CEO, Jensen Huang, revealed some of the most exciting technological innovations during his keynote presentation at Computex 2024 in early June. Surpassing Apple to become the second most valuable company in the U.S., NVIDIA and their research team is working on finding breakthroughs that will drive further adoption of AI. Below we explain a […]
- 1
- 2