We raised a Series A! Read a post from our CEO, Zhen Lu: 1M devs and the cloud we're building next.

Blog

Introducing Serverless CPU: High-Performance VMs Without GPUs

Our new Serverless CPU offering lets you launch high-performance containers without GPUs, perfect for lighter workloads, dev tasks, and automation.

Introducing Serverless CPU: High-Performance VMs Without GPUs

We are thrilled to introduce the latest addition to the Runpod platform: Serverless CPU. This feature allows you to create high-performance VM containers with up to 3.75 GHz deviated cores, DDR5 memory, and NVME SSD storage.

With Serverless CPU, you have the flexibility to choose between Compute-Optimized or General Purpose CPUs and various configurations to suit your specific needs. Whether you require high compute power for intensive tasks or a balanced setup for general purposes, we've got you covered.

Getting Started:

  1. Create a New Endpoint: Select the CPU option to access our powerful VM containers.
  2. Choose Your Configuration: Opt for either Compute-Optimized or General Purpose CPUs, based on your workload requirements.
  3. Deploy and Scale: Enjoy the seamless experience of deploying and scaling your applications with Runpod's Serverless CPU.

Why Choose Serverless CPU over Serverless GPU?

While GPUs are well-known for their exceptional performance in parallel processing tasks, such as deep learning and complex computations, there are scenarios where CPUs are more suitable. Here are a few reasons why you might choose Serverless CPU over Serverless GPU:

  1. Cost Efficiency: CPUs can be more cost-effective for workloads that do not require the intensive parallel processing power of GPUs. For general-purpose tasks, data processing, and applications that rely on sequential processing, CPUs provide a budget-friendly solution.
  2. Versatility: CPUs are versatile and can handle a wide range of tasks beyond just parallel computations. They are ideal for running a variety of applications, including web servers, databases, and more, making them a great choice for diverse workloads.
  3. Ease of Integration: Many applications and software are optimized for CPU usage. When your workload aligns with these applications, using a CPU can simplify integration and deployment processes.
  4. Resource Availability: In some cases, GPU resources might be limited or in high demand, leading to potential delays or higher costs. CPUs, being more widely available, can provide a reliable alternative.

Embrace the power of Runpod's Serverless CPU and elevate your application's performance today!

For a step-by-step guide on how to get started, check out our tutorial: Run an Ollama Server on a Runpod CPU.

Start Up a CPU Serverless Endpoint

‍

Author profile: Brendan McKeag

Blog Posts

Related articles

View All
What's new in Runpod Serverless: Faster cold starts, batch inference, and no-Docker deploys

What's new in Runpod Serverless: Faster cold starts, batch inference, and no-Docker deploys

Whether you're already running production endpoints on Runpod or you're sizing us up for the first time, here's a plain-language tour of what Runpod Serverless does today, why it's faster and cheaper than it was six months ago, and how to deploy your first endpoint in minutes.

All
What's new in Runpod Serverless: Faster cold starts, batch inference, and no-Docker deploys

Build what’s next.

Build, train, and scale AI workloads on Runpod with cloud GPUs, Serverless, and Clusters.