Runpod Blog.

Learn how to deploy Python machine learning models on Runpod without touching Docker. This guide walks you through using virtual environments, network volumes, and Runpod’s serverless API system to serve custom models like Bark TTS in minutes.

Runpod is now an official sponsor of StockDory, a rapidly evolving open-source chess engine that improves faster than Stockfish. StockDory offers deep positional insight, lightning-fast calculations, and full customization—making it ideal for anyone looking to explore AI-driven chess analysis.

Runpod’s new FlashBoot technology slashes cold-start times for serverless GPU endpoints, delivering speeds as low as 500ms. Available now at no extra cost, FlashBoot dynamically optimizes deployment for high-volume workloads—cutting costs and improving latency dramatically.

This post features a video tutorial by generativelabs.co that walks users through deploying a Stable Diffusion A1111 API using Runpod Serverless. It covers setup, Dockerfile and handler edits, endpoint deployment, and testing via Postman—great for beginners and advanced users alike.

While Oobabooga is a popular choice for text-based AI roleplay, KoboldAI offers a powerful alternative with smart context handling, more flexible editing, and better long-term memory retention. This guide compares the two frontends and walks through deploying KoboldAI on Runpod for writers and roleplayers looking for a deeper, more persistent AI interaction experience.

Oobabooga now supports up to 8192 tokens of context, up from the previous 2048-token limit. Learn how to upgrade your install, download compatible models, and optimize your setup to take full advantage of expanded memory capacity in longform text generation.

Runpod now offers access to NVIDIA’s powerful H100 GPUs, designed for generative AI workloads at scale. These next-gen GPUs deliver 7–12x performance gains over the A100, making them ideal for training massive models like GPT-4 or deploying demanding inference tasks.