In an effort to lower infrastructure costs and optimize workloads across multiple industries, Google Cloud is introducing G2 VMs, a new addition to the Compute Engine GPU family. Powered by NVIDIA L4 Tensor Core GPU, G2 VMs are designed to enhance AI, HPC, and various other applications on the platform. This new technology aims to revolutionize AI inference workloads and generative AI within the Google Cloud ecosystem.
The growing need for cloud GPUs comes as industries look to decrease costs while increasing the adoption of AI. G2 VMs are the first cloud virtual machines with the NVIDIA L4 Tensor Core GPU, bringing powerful capabilities that cater to large inference AI workloads and generative AI.
Transitioning from NVIDIA A10G GPUs to G2 instances can result in up to a 40% reduction in production infrastructure costs. Furthermore, by upgrading from NVIDIA T4 GPUs to L4 GPUs, users can experience performance improvements between 2 and 4 times. The new offering provides a universal GPU solution for accelerations in HPC, graphics, and video transcoding.
Currently, in private preview, G2 VMs offer the ability to scale from a single GPU up to eight GPUs. This scalability and flexibility cater to a wide range of computational needs, from small-scale projects to large, data-intensive workloads.
G2 VMs are not only compatible with Vertex AI, GKE, and GCE, but they also offer optimization for different performance requirements and budgets. This integration ensures a seamless end-to-end infrastructure deployment experience for users of various needs.
Vertex AI provides G2 VM users with access to generative AI models and technologies. The user-friendly interface and automated workflows make the integration process smooth and efficient. Serving models for video, text, images, and audio no longer require manual optimizations, further streamlining the process.
The Ada Lovelace architecture, integrated into NVIDIA’s L4 GPUs, is ideal for ML applications such as language model training, image classification, object detection, automated speech recognition, and language translation. Performance stats for the L4 GPU showcase its capabilities at up to 30 TFLOPS for FP32 operations and 242 TFLOPs for FP16 operations, making it a powerhouse of machine learning capabilities. Additionally, the L4 GPUs support a variety of data types, including FP8, INT8, BFLOAT16, and TF32.
In conclusion, the introduction of G2 VMs powered by NVIDIA L4 Tensor Core GPUs in Google Cloud marks a significant milestone in the adoption and advancement of AI across various industries. The cost and performance benefits, scalability, flexibility, end-to-end infrastructure deployment, and seamless integration with other platforms and services ensure that G2 VMs facilitate a new era of innovation and success in the world of AI.
Up until working with Casey, we had only had poor to mediocre experiences outsourcing work to agencies. Casey & the team at CJ&CO are the exception to the rule.
Communication was beyond great, his understanding of our vision was phenomenal, and instead of needing babysitting like the other agencies we worked with, he was not only completely dependable but also gave us sound suggestions on how to get better results, at the risk of us not needing him for the initial job we requested (absolute gem).
This has truly been the first time we worked with someone outside of our business that quickly grasped our vision, and that I could completely forget about and would still deliver above expectations.
I honestly can't wait to work in many more projects together!
![The ‘Giveaway Piggy Back Scam’ In Full Swing [2022]](https://www.cjco.com.au/wp-content/uploads/pexels-nataliya-vaitkevich-7172791-1-scaled-2-683x1024.jpg)
Disclaimer
*The information this blog provides is for general informational purposes only and is not intended as financial or professional advice. The information may not reflect current developments and may be changed or updated without notice. Any opinions expressed on this blog are the author’s own and do not necessarily reflect the views of the author’s employer or any other organization. You should not act or rely on any information contained in this blog without first seeking the advice of a professional. No representation or warranty, express or implied, is made as to the accuracy or completeness of the information contained in this blog. The author and affiliated parties assume no liability for any errors or omissions.
