---
title: "Slides: Under 5 minutes to a deployed LLM endpoint — Audry Hsu, RunPod"
category: "slides"
video_id: "ILdE7FaAjVA"
sourceLabels: ["Public YouTube video frames", "Public YouTube metadata"]
---

# Slides: Under 5 minutes to a deployed LLM endpoint — Audry Hsu, RunPod

## Source Video
[Under 5 minutes to a deployed LLM endpoint — Audry Hsu, RunPod](https://www.youtube.com/watch?v=ILdE7FaAjVA)

## Relationship To World's Fair 2026
These slides are extracted from a public AI Engineer YouTube video connected to World's Fair 2026. Speaker-matched clips are supporting context unless later confirmed as exact session recordings; official livestream recordings are day-level/event-level source material.

## Related Scheduled Sessions
- No individual scheduled session mapping has been assigned yet; treat this as an event livestream deck.

## Extracted Slides
![[assets/slides/ILdE7FaAjVA/slide-001.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/ILdE7FaAjVA/slide-001.html)
- AI slide classifier: `content_slide` confidence `0.98`
- Text source: agent_vision.

Slide text:

> Introducing Runpod
> The foundational platform for building, running, and scaling custom AI systems.

![[assets/slides/ILdE7FaAjVA/slide-002.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/ILdE7FaAjVA/slide-002.html)
- AI slide classifier: `content_slide` confidence `0.97`
- Text source: agent_vision.

Slide text:

> Why Runpod Exists

![[assets/slides/ILdE7FaAjVA/slide-003.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/ILdE7FaAjVA/slide-003.html)
- AI slide classifier: `content_slide` confidence `0.92`
- Text source: agent_vision.
- OCR decision: ready — Small bullet text and multi-column layout are better suited for OCR.

Slide text:

> Serverless

![[assets/slides/ILdE7FaAjVA/slide-005.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/ILdE7FaAjVA/slide-005.html)
- AI slide classifier: `content_slide` confidence `0.89`
- Text source: agent_vision.
- OCR decision: ready — Dense UI screenshot and small repository metadata are better handled by OCR.

Slide text:

> vLLM

![[assets/slides/ILdE7FaAjVA/slide-006.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/ILdE7FaAjVA/slide-006.html)
- AI slide classifier: `content_slide` confidence `0.96`
- Text source: none.
- OCR decision: ready — Code-heavy slide with small monospace text is OCR-suitable.

### Hidden Non-Slide Evidence
- [`slide-004.jpg`](/assets/slides/ILdE7FaAjVA/slide-004.jpg) — `title_card` confidence `0.71`; Brand/interstitial card with logo only, not substantive presentation content.
- [`slide-007.jpg`](/assets/slides/ILdE7FaAjVA/slide-007.jpg) — `title_card` confidence `0.74`; End-card / brand logo screen, not a substantive content slide.

Classification audit: `raw/sources/slide-ai-classification/slides/ILdE7FaAjVA/audit.json`

## Slide-Derived Subjects To Review
Subject extraction uses video title, related session titles/descriptions, transcript context, and OCR text when available. OCR is best-effort and should be reviewed against the embedded slide images.