Summary
In this episode, we look at leveraging the end user's hardware and WebGPU to run large language models directly in the user's browser.rails artificial intelligence stimulusjs 20:25
Chapters
- Introduction (0:00)
- Picking a model (3:43)
- Adding Web LLM (4:55)
- Setting up the chat stimulus controller (5:12)
- Setting up the view (8:11)
- Clear the local storage (9:53)
- Creating the submit functionality (10:39)
- Demo (14:18)
- Streaming the response (14:46)
- Stream Demo (17:36)
- Final thoughts (18:19)
Pro Monthly
$
19
/mo
Access to Pro Episodes
Invite to Slack Channel
Priority Suggestions
Ad Free
Pro Annual
$
190
/yr
Access to Pro Episodes
Invite to Slack Channel
Priority Suggestions
Ad Free