Latest AI and tech news
Run the work that can wait as Batch Inference and keep real-time capacity for live traffic.
Global Volumes mount like a network volume but run on object storage. That changes what you should put on them.
GLM-5.3 is now available on Runpod's public endpoints. Here's how to try it in the Playground, call it with curl, and use it through the OpenAI SDK in Python.
Global volume file systems work in some key ways that are different from network or local volumes - if you've got questions, this will hopefully help explain.
Our PyTorch templates now cover 2.6 through 2.13 across multiple CUDA and Ubuntu versions, with a new CUDA dropdown in the Pod deploy flow so you can match a template to your GPU and workload.
Why your balance can drop even when nothing succeeds, how to find where the money went, and how to keep it from happening again.
Flash now ships a first-class Nix flake. Run the CLI with nix run github:runpod/flash, get a pinned dev shell, and send GPU work to Runpod Serverless.
Less of the work around your compute is yours to maintain this quarter, from one API for the whole platform to one account for your whole company. Plus the deadlines for v1 and GraphQL users.
You can teach an open-weight LLM to text like a specific persona: their slang, their reply length, their humor, even how they write in a roleplay scene, creative writing exercise, or chatbot customer interactions. All it takes is some chat logs (synthetic or real), a few hours of data prep, and a si
Attach a Global Volume to a Runpod Serverless endpoint and your workers start in any data center with your GPU types. Store model weights once, read anywhere.
Deploy OpenJev, a 27B decision model that returns structured answers and confidence scores, on a Runpod Serverless load balancer endpoint, then send your first request with cURL and Python.
The State of AI Compute shows what teams actually deploy: agents are 8% of users but drive 24% of revenue, a new model version can take over its family's workloads in about a month, and lower precision is becoming a production strategy for large models.
Lost on how to connect to your pod with SSH? Start here.
Keep the platform your developers already use. Add reserved capacity, company-wide controls, compliance, invoicing, and hands-on support.
Global Volumes provide elastic, region-independent storage you can mount into a Pod in any Runpod data center.
Selecting the right serving engine for your embedding model can dramatically outperform hardware upgrades, yielding up to an 11x throughput increase on the same GPU.
When a private GPU pool beats on-demand GPUs, how reserved capacity is billed, what happens when traffic bursts above the pool, and what usage data to bring before you commit.