The iteration cycle before Flash: commit, push, build a Docker image, pull it from the registry, load it onto a server, allocate a GPU, then find out if it works. Audrey Hsu demos what replacing that with a single decorator looks like — add `@flash.endpoint` to an async Python function and it deploys to GPU cloud from your IDE, with hot reload so a model swap is one line of code rather than a container rebuild.

The second demo chains three models: Qwen 3 generates image prompts, DreamShaper renders them, Nano Banana 2 composes the results into a single photo. H100 pricing is $0.00116 per second, charged only while a worker is handling a request. RunPod's recommendation: start with pods while experimenting, switch to serverless when you need hundreds of workers autoscaling across data centers.

Speaker info:
- https://www.linkedin.com/in/audry-hsu/

AI Engineer

RunPod's Audrey Hsu demonstrates Flash, a Python SDK that lets developers deploy GPU-accelerated functions directly from their local IDE without the typical commit-build-push-deploy cycle. Using a decorator pattern, Flash packages async Python functions and runs them on RunPod's GPU cloud with hot file reload for rapid iteration. The demo shows image generation with Stable Diffusion models, switching between SDXL Turbo and DreamShaper, and a multi-step pipeline combining Qwen 3 for prompt engineering, DreamShaper for image generation, and Gemini for photo composition. RunPod offers pods, serverless, and cluster options with per-second billing, and has reached $120M ARR across 30+ data centers in 10 countries.

GPU Cloud Deployment Without Leaving Your IDE — Audry Hsu, RunPod