RunPod Blog
AI news source. Articles are auto-selected and adapted by Hamidun News editors.
Latest publications
Runpod shows how to run diffusion models on JAX in GPU pods
Runpod has published a guide to running diffusion models on JAX, from setting up the environment in a GPU pod to a first inference run, with no local hardware to wrangle.
Runpod Sponsors TreeHacks 2026: 36 Hours of GPU Compute at Stanford
Runpod sponsored TreeHacks 2026 at Stanford. Over 36 hours, teams built projects on cloud GPUs, including GPU-accelerated cancer drug discovery and other prototypes.
Runpod Connects to Cursor and Claude Code via MCP: GPU Infrastructure From the Chat Window
Runpod now supports MCP: Cursor and Claude Code can launch Pods, deploy endpoints and manage GPU infrastructure without opening the web console.
RunPod Breaks Down 4 Quantization Methods: Going From FP16 to INT4 Cuts Memory 4x
RunPod compared post-training quantization, QAT, mixed precision and dynamic quantization. Moving from FP16 to INT4 cuts weight memory fourfold, but at a cost in accuracy.
Genmo's Mochi 1: An Open 10B-Parameter Video Model Under Apache 2.0
Genmo has released Mochi 1, a 10B-parameter diffusion text-to-video model under Apache 2.0. RunPod has already shown how to deploy it in the cloud.
Runpod's roundup: Llama-2 with a 32k-token context and SDXL 1.0 now publicly available
Runpod's second RoundUp logs two releases: Llama-2 with a 32 thousand-token window and the public SDXL 1.0. We look at what's behind the numbers and what they cost in VRAM.
RunPod: 4 A100 GPUs in the cloud cost $124 000 less than on-prem over 3 years
RunPod compared its cloud with an in-house cluster of four A100s over three years and claims savings of more than $124 000. Here is what holds up in that figure and what doesn't.
Runpod: How to Set Up Full SSH for SCP and IDEs on GPU Pods
Runpod has published a guide to setting up a real SSH daemon on GPU pods. It enables SCP, SFTP and IDE connections, which the default proxy access cannot do.
Image Mixer blends multiple images into a single input for Stable Diffusion img2img
RunPod walks through Image Mixer, a tool that blends several images into one hybrid source for Stable Diffusion img2img. The guide covers installation and workflow.
Runpod Sponsors Project Odyssey, CivitAI's Open-Source AI Film Contest
GPU cloud Runpod is backing CivitAI's Project Odyssey AI film contest. The announcement discloses no prize pool or credit amount, and the post looks like archived 2024 material.
Deep Cogito trained its Cogito v1 family on Runpod infrastructure on the road to ASI
San Francisco startup Deep Cogito trained its open Cogito v1 models on Runpod's cloud. The company's stated goal is artificial superintelligence; the lineup spans 3B to 70B parameters.
Runpod shows how to deploy Llama 3.1 8B on vLLM without your own servers
Runpod Blog has published a guide to running Llama 3.1 8B Instruct on vLLM via Serverless: GPU time is billed per second, and workers scale up from zero under load.
Runpod shows how to build your own Vlad Diffusion template for cloud GPUs
Runpod has published a guide to building a custom Vlad Diffusion template: the popular Stable Diffusion fork launches on a cloud GPU from a ready-made image, with no manual setup.
RunPod Publishes Guide to Moving from the OpenAI API to a Self-Hosted Open-Weight LLM
RunPod has published a guide to migrating from the OpenAI API to a self-hosted open-weight LLM, aimed at teams hitting rate limits and growing token bills.
Runpod shows how to spin up your own API on Serverless in four steps
Runpod released a Serverless guide: a Python handler function, five API routes, and deployment from a Docker image with per-second GPU billing. Here's how it works.
Runpod shows how GuideLLM helps squeeze the most out of vLLM
Runpod has published a GuideLLM guide: the tool simulates production load on vLLM and measures TTFT, ITL and throughput, so teams can calculate GPU costs more accurately.
RunPod Shows How to Deploy Stable Diffusion A1111 as a Serverless API
A generativelabs.co video tutorial walks through deploying Stable Diffusion A1111 as an API on RunPod Serverless: the GPU spins up on demand, with no payment for idle time.
Runpod Shows How to Spin Up a Serverless GPU Worker from a GitHub Template in Three Steps
Runpod walks through the path from a GitHub template to a working Serverless endpoint: create, test, deploy. You pay only for the time spent processing requests.