Delska’s Post

GKE provides a scalable, resilient, secure and cost-effective platform for running containerized batch workloads with both a hands-off Autopilot experience and highly customizable Standard mode that can be specified to fit the needs of your organization. Having deep integration with Google Cloud services, access to all Compute Engine VM families, CPU and accelerator architectures and the Kubernetes-native Job queueing capabilities of Kueue, GKE is ready to be the new home for your batch workloads. It gives you the ability to operate large computational platforms, simplifying multitenancy, scale, and performance with cost optimization. #googlekubernetesengine #kubernetes #batchprocessing #googlecloud

Today Google announced #Axion - a new custom CPU that is built on the standard Armv9 architecture and instruction set. Google Cloud instances built with it will have up to 30% better performance than the fastest general-purpose Arm-based instances available in the cloud today, up to 50% better performance and up to 60% better energy-efficiency than comparable current-generation x86-based instances. Software that runs on Arm-based servers and VMs today, will run on new #C4A VMs with limited-if-any code rewrites making it easier for customers to deploy Arm workloads on Google Cloud. This showcases the real strength of Arm #ecosystem. https://lnkd.in/g2nn6zC9

Here’s a tutorial on how to deploy Large Language Models like Llama and Mistral through huggingface on IBM Cloud and inference them easily. For inferencing, we don’t need GPUs, we can run LLMs at lower checkpoints on CPUs itself. It takes less than 10 minutes to deploy the models and consume them on IBM Cloud! https://lnkd.in/gu7eJu6X #ibmcloud #generativeai #llms #aiinfrastructure Krishna Balaga

Understand the basics of vpc networking and deployment of private LLMs #llmsforall

🚀 Day 6 of the 60-Day AWS Challenge! 🚀 Welcome to Day 6 ! Today, let's explore Amazon EC2 (Elastic Compute Cloud) through some key questions: Objective: Dive deep into understanding Amazon EC2 and its impact on modern computing infrastructure. Plan for Today: Q.1 What is AWS Elastic Compute Cloud (EC2)? Q.2 What are the features of EC2? Q.3 What advantages does EC2 offer? Q.4 What purchasing options are available for optimizing costs with Amazon EC2? Q.5 What are the storage options available for instances on Amazon EC2? Q.6 What options does Amazon EC2 offer for selecting resources such as CPU, memory, storage, and networking for running applications? Let's explore these questions together and gain a deeper understanding of Amazon EC2's role in shaping the landscape of cloud computing! 💻☁️ Share your insights and experiences about Amazon EC2 in the comments below! Let's dive into the world of AWS and uncover its endless possibilities! ☁️🚀 #AmazonEC2 #EC2Features #EC2Advantages #EC2CostOptimization #EC2StorageOptions #EC2ResourceSelection #Day6 #AWSChallenge https://lnkd.in/g_asfjXs

Much of what organizations need for compute, storage, and networking can be found in HPE’s expansive GreenLake hybrid cloud services platform – and much of the AI work being done by enterprises, institutions, and others is being done in the cloud – a lot of HPC is still being done on premises. Companies Need On-Premise #HPC - And For More Than #AI, Too. #HPEGreenLake

日本が誇るスーパーコンピューター「富岳」の機能へのバーチャルアクセスを可能とする「バーチャル富岳」が理研様より発表されました。AWSが科学の発展に寄与する機会を見ることができ、嬉しく思います。 ----以下、引用となります--- “Virtual Fugaku” allows users to access a highly optimized software suite designed for Fugaku on cloud services and non-Fugaku computers. This makes it easier for a wider audience to utilize Fugaku’s research capabilities and advanced computing platforms, potentially driving further scientific, technological, and industrial advancements.

Absolutely, it's impressive how NVIDIA leads the way in high-performance networking. Their breakdown of how OCI utilizes innovative RDMA-powered networking on Ethernet for various workloads is enlightening! OCI, the Cloud to run it faster, for less, and more secure. Try it! #HPC #CloudInfrastructure #OCI #Oracle #NVIDIA #AIML #HPC #CloudInfrastructure #OCI #Oracle

On my blog: Deploying LLMs via Hugging Face on IBM Cloud #TGI #HuggingFace #Mistral #LLM #AI https://lnkd.in/eCWieKqg