Today NVIDIA LaunchPad hits new heights. LaunchPad is a hands-on environment where enterprise customers can use NVIDIA AI Enterprise servers in a vSphere 7 environment managed by Equinix free of charge for 2-4 weeks. Although enterprises are more than welcome to use this service with real workloads they are considering deploying on an NVIDIA environment, they can also go through labs that NVIDIA has created that allow IT professionals to become comfortable with using NVIDIA-enabled servers.
NVIDIA LaunchPad Enabling Enterprise AI
NVIDIA feels that one of the reasons that more companies are not using more AI is the unfound fear in the complexity of setting up an AI environment. With this in mind, labs were designed to dissuade these fears for two different types of AI professionals in mind; IT administrators and managers that need to stand up and support AI environments and AI practitioners that need to use them.
Offering NVIDIA LaunchPad will help build confidence in their ability to support and use AI before investing IT budget in Ai endeavors. Furthermore, as customers can actually deploy their AI workloads on LaunchPad, they can see the value of their AI project with an NVIDIA GPU, in an exceedingly low-friction sort of way.
NVIDIA LaunchPad – How it Works
Once the user signs up for the environment they access the environment via a URL and secure credentials. The environment that we saw was a Dell EMC PowerEdge R750 NVIDIA-Certified System with an NVIDIA A30 GPU. NVIDIA indicated that other servers and vendors may also be used, and the systems may be equipped with an NVIDIA A30 or a T4 GPU depending on use case.
Regardless of the hardware all the systems will be using NVIDIA AI Enterprise which NVIDIA describes as
“an end-to-end, cloud-native suite of AI and data analytics software, optimized, certified, and supported by NVIDIA to run on VMware vSphere with NVIDIA-Certified Systems. It includes key enabling technologies from NVIDIA for rapid deployment, management, and scaling of AI workloads in the modern hybrid cloud.”
The labs have vSphere preinstalled and users access a vSphere client from the URL that is given to them by NVIDIA.
As mentioned, NVIDIA makes it easy for two core personas to negotiate LaunchPad. IT administrators have labs that walk them through the steps involved in configuring VMs to use GPUs. AI practitioners have labs they can go through, for example, that walks them through creating an Ubuntu VM, associating an NVIDIA GPU to it, acquiring and adding an NVIDIA driver to the OS, acquiring an NVIDIA API key and software, licensing the VM to use the GPU.
As much AI software is container-based, LaunchPad walks trialists through installing Docker, the container tool kit for NVIDIA, and installing Tensor flow and run AI examples on it. As this is a real environment, users can also build and deploy their own AI projects on it.
Closing Thoughts
We are excited about this free offering from NVIDIA as it reminds us of VMware Hands-on-labs and VMware TestDrive but with the added benefit of allowing you to work with your own AI project on it. And given the difficulty for some to even come by this class of GPU in the first place, NVIDIA LaunchPad is perhaps the easiest way to get relatively immediate access to one.
Lastly, NVIDIA has done an excellent job pulling together all of the components to make this so easy. The documentation is phenomenal and jumping straight into a fully deployed vCenter, with GPU, is a great head start. Once a customer finishes their LaunchPad experience after a few weeks, because this is all in the VMware hypervisor, it’s simple to migrate VMs to Equinix, some other cloud compute instance with GPU, or an environment of the customer’s choice, if they like.
We have a few more weeks with NVIDIA LaunchPad and will report back with more depth on our experience.
For more information on NVIDIA LaunchPad click here.
Amazon