# Snowflake's Boxin Jiang on optimizing multimodal AI pipelines at scale

> Original title: 6 | @Snowflake

- Source: LMSYS Org
- Published: 2026-11-04T22:51:51.000Z
- Bad Influence: https://badinfluence.news/items/yzr61qwojkkp8lzvz8hb5xg5d
- Original: https://x.com/lmsysorg/status/2118114026391785713

## Summary

LMSYS Org shares a post from Snowflake on optimizing multimodal AI pipelines at scale. Boxin Jiang describes combining model, compiler, and query optimizations to make these pipelines reliable and cost-effective.

## Post

6 | @Snowflake 
Optimizing Multimodal AI Pipelines at Scale

Boxin Jiang on combining model, compiler, and query optimizations to make multimodal AI pipelines reliable and cost-effective.

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHWUMTzlakAEI9_y.jpg&mode=thumb&exp=1794096000&sig=194280517ae31ff9)