Runpod Blog
Articles about Runpod Blog
Performing your first LLM fine-tune on Runpod with Axolotl, and how to host it after
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 single GPU pod.
Runpod Just Got Native in Your AI IDE
Runpod now integrates directly with AI IDEs like Cursor and Claude Code using MCP. Launch Pods, deploy endpoints, and manage infrastructure, right from.
The Dos and Don’ts of VACE: What It Does Well, What It Doesn’t
VACE introduces a powerful all-in-one framework for AI video generation and editing, combining text-to-video, reference-based creation, and precise.
A1111 Serverless API – Step-by-Step Video Tutorial
This post features a video tutorial by generativelabs.co that walks users through deploying a Stable Diffusion A1111 API using Runpod Serverless. It.
How to Create a Custom API on Runpod Serverless
Learn how to build and deploy a simple API using Runpod's Serverless platform. This guide covers writing a worker, exposing endpoints, and testing your.
How to Manage Funding Your Runpod Account
This guide breaks down everything you need to know about billing on Runpod, how credits are applied, what gets charged, and how to set up automatic or.
Boost vLLM Performance on Runpod with GuideLLM
Learn how to use GuideLLM to simulate real-world inference loads, fine-tune performance, and optimize cost for vLLM deployments on Runpod.
Faster-Whisper: 3x Cheaper, 4x Faster Transcription
Runpod's new Faster-Whisper endpoint delivers 2-4x faster transcription speeds than the original Whisper API, at a fraction of the cost.
Exploring Runpod Serverless: Create Workers From Templates
Learn how to quickly create, test, and deploy Runpod Serverless workers using GitHub templates, accelerating AI workloads with pay-per-use efficiency and.
Creating a Vlad Diffusion Template for Runpod
Want a custom spin on Stable Diffusion? This post shows you how to create and launch your own Vlad Diffusion template inside Runpod.
Built on Runpod: How Cogito Trained Models Toward ASI
San Francisco-based Deep Cogito used Runpod infrastructure to train Cogito v1, a high-performance open model family aiming at artificial.
From OpenAI API to Self-Hosted Model: A Migration Guide
How to switch from OpenAI's API to a self-hosted LLM built on open-source models on Runpod, for teams tired of usage limits and API costs.
How to Run Serverless AI and ML Workloads on Runpod
Learn how to train, deploy, and scale AI/ML models using Runpod Serverless. This guide covers real-world examples, deployment best practices, and how.
Deploy Llama 3.1 With vLLM on Runpod Serverless
Learn how to deploy Meta's Llama 3.1 8B Instruct model using the vLLM inference engine on Runpod Serverless for blazing-fast performance and scalable AI.
Hybridize Images With Image Mixer Before Running Through img2img
Image Mixer lets you blend multiple source images into a hybrid input for img2img in Stable Diffusion. This guide walks through setup, usage, and how to.
Runpod RoundUp 2: 32k Token Context LLMs, StabilityAI
This week's Runpod RoundUp covers major releases including Llama-2 with 32k context support, SDXL 1.0's public release, and StabilityAI's new Stable.
GPU Cloud vs On-Prem Clusters: A Cost Breakdown
We crunched the numbers: deploying 4x A100s on Runpod's GPU cloud can save over $124,000 versus an on-prem cluster across 3 years. Learn why cloud beats.
Runpod Sponsors CivitAI’s Project Odyssey 2024
Runpod is proud to support Project Odyssey, CivitAI’s groundbreaking open-source AI film competition. Learn how we’re powering creators around the world.
Mochi 1: New State of the Art in Open-Source Text-to-Video
Mochi 1 pushes the boundaries of open-source video generation. Learn what makes it special, what’s new in v1, and how to deploy it on Runpod.
How to Achieve True SSH in Runpod
This tutorial guides users through setting up a true SSH daemon on Runpod, enabling functionalities like SCP and IDE connections. It covers selecting a.
Runpod Roundup 5: Vision, Code LLMs, and Bias Detection
his week's roundup covers Alibaba's vision-language model Qwen-VL, Meta's new code-focused LLM Code Llama, and FACET, a benchmark for detecting bias in.
RAG vs. Fine-Tuning: Which Strategy is Best for Customizing LLMs?
RAG and fine-tuning are two powerful strategies for adapting large language models (LLMs) to domain-specific tasks. This post compares their use cases.
Qwen3 Released: How Does It Stack Up?
Alibaba's Qwen3 is here, with major performance improvements and a full range of models from 0.5B to 72B parameters. This post breaks down what's new, how.
RAG vs. Fine-Tuning: Which Is Best for Your LLM?
Retrieval-Augmented Generation (RAG) and fine-tuning are powerful ways to adapt large language models. Learn the key differences, trade-offs, and when to.
Quantization Methods Compared: Speed vs. Accuracy in Model Deployment
Explore the trade-offs between post-training, quantization-aware training, mixed precision, and dynamic quantization. Learn how each method impacts model.
Supercharge Your LLMs with SGLang: Boost Performance and Customization
Discover how to boost your LLM inference performance and customize responses using SGLang, an innovative framework for structured LLM workflows.
Streamline GPU Cloud Management with Runpod’s New REST API
Runpod’s new REST API lets you manage GPU workloads programmatically, launch, scale, and monitor pods without ever touching the dashboard.
Partnering with Defined AI to Bridge the Data Wealth Gap
Runpod and Defined.ai launch a pilot program to provide startups with access to high-quality training data and compute, enabling sector-specific.
The simple way to run AI on GPUs (without a Kubernetes team)
Understand the real operational cost of running AI inference on Kubernetes, from cluster management and scaling to reliability and developer overhead.
What hackers built on Runpod at TreeHacks 2026
We sponsored TreeHacks 2026 at Stanford, where teams built on Runpod across 36 hours, shipping projects ranging from GPU-accelerated cancer drug discovery.
Cold starts were never the real problem
Flash deploys Python functions as serverless GPU endpoints in under 30 seconds. FlashBoot cuts serverless GPU inference cold starts to under 200ms.
Train Your Own Video LoRAs with Diffusion-Pipe
A simple guide to training custom video LoRAs using Diffusion-Pipe on Runpod, perfect for creators and AI enthusiasts.
Event Streaming and CDC Infrastructure at Runpod
Learn how Runpod built a real-time event streaming platform using Change Data Capture (CDC), the transactional outbox pattern, and the MySQL binlog to replace database polling, simplify consumers, and automate analytics.
Global Volumes for Serverless
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.
Introduction to vLLM and PagedAttention
Learn how vLLM achieves higher throughput than Hugging Face Transformers by using PagedAttention to eliminate memory waste, boost inference.
Avoid Errors by Selecting the Proper Resources for Your Pod
Common errors when spinning up pods often stem from insufficient container space or RAM/VRAM. This post explains how to identify and fix both issues by.
Inference, optimized: How we benchmarked Runpod Overdrive
See how Runpod benchmarked four models across sixteen workload profiles to measure Overdrive inference performance, efficiency, and scaling behavior.
Why AI is now an infrastructure problem
Start AI Infrastructure 101, a seven-part series covering the platform, lifecycle, and infrastructure decisions behind production AI systems.
Deploy OpenJev on Runpod Serverless (Step-by-Step Guide)
Learn how to deploy OpenJev, a 27B structured-decision model, on a Runpod Serverless load balancer endpoint, then send requests with cURL and Python.
How to Cut LLM Inference Latency and Cost
Learn how to reduce LLM inference costs and latency using quantization, vLLM, SGLang, and speculative decoding without upgrading your hardware.
State of AI Compute: Insights from 1.2M Developers
Runpod data from 1.2 million accounts shows how teams actually use AI compute, from agent-led deployments to open model upgrades and quantized inference.
Runpod Partners With Defined.ai for AI Development
Runpod announces a partnership with Defined.ai to offer ethically sourced speech and text datasets to AI developers, starting with a pilot program to.
Runpod Serverless Scaling: Optimize Performance and Cost
Learn how to optimize your serverless GPU deployment on Runpod to balance latency, performance, and cost. From active and flex workers to Flashboot and.
Run Very Large LLMs Securely with Runpod Serverless
Deploy large language models like LLaMA or Mixtral on Runpod Serverless with strong privacy controls and no infrastructure headaches. Here’s how.
Runpod Partners With Data Science Dojo for LLM Bootcamps
Runpod has partnered with Data Science Dojo to power their Large Language Model bootcamps, providing scalable GPU infrastructure to support hands-on.
Set Up a Chatbot with Oobabooga on Runpod
This tutorial walks you through deploying Oobabooga's Text Generation WebUI using the Runpod template. Includes steps for loading Pygmalion 6B and.
Run Llama 3.1 with vLLM on Runpod Serverless
Discover how to deploy Meta's Llama 3.1 using Runpod's new vLLM worker. This guide walks you through model setup, performance benefits, and step-by-step.
Runpod Enterprise simplifies governance and billing
Your developers already love Runpod and now we're adding reserved capacity, company-wide controls, compliance, invoicing, and hands-on support.
Where Did My Files Go? A Straight Guide to Runpod Storage
Three storage layers, three lifetimes, and how to get your work onto the right one before you lose it instead of after.